Skip to content
MCP server

Markdown Vault MCP

Search, read and write a folder of Markdown notes with hybrid keyword and meaning search

Pricing
Free
Platforms
CLI, self-hosted, Linux
Runs
Locally or Remotely
Version
6.1.2
Listing updated
2 days ago

About Markdown Vault MCP

Markdown Vault MCP is a free MCP server for files and documents. It can run locally on your machine or as a hosted remote server.

Point it at a folder of Markdown notes, and an Obsidian vault works as it is, and an assistant can search, read and edit them. Keyword search uses SQLite FTS5, and once an embedding provider is configured it adds search by meaning, fused by Reciprocal Rank Fusion with vectors held in SQLite, files or PostgreSQL. Results are short snippets, and read returns the whole section.

Writes are on by default and can be turned off with MARKDOWN_VAULT_MCP_READ_ONLY. Replacing a file needs the etag from reading it, per-folder _conventions.md rules reach the client as it writes, and an optional Git layer commits each write with history, diffs and read-back of an overwritten note. Link tools report backlinks, outlinks, broken links and the path between two notes, and YAML frontmatter fields become search filters.

The server runs over stdio or Streamable HTTP, and individual tools can be hidden through allow and deny lists. Embeddings can come from Ollama or OpenAI. A CLI can query a running vault remotely.

Install

Run in a terminal

claude mcp add markdown-vault-mcp --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env VOYAGE_API_KEY='<VOYAGE_API_KEY>' --env MARKDOWN_VAULT_MCP_CLIENT_TOKEN='<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>' --env MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN='<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>' --env MARKDOWN_VAULT_MCP_GIT_TOKEN='<MARKDOWN_VAULT_MCP_GIT_TOKEN>' --env MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET='<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>' --env MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN='<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>' --env MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN='<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>' --env MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY='<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>' -- uvx markdown-vault-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "markdown-vault-mcp": {
      "command": "uvx",
      "args": [
        "markdown-vault-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "MARKDOWN_VAULT_MCP_CLIENT_TOKEN": "<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>",
        "MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN": "<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>",
        "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<MARKDOWN_VAULT_MCP_GIT_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>",
        "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "markdown-vault-mcp": {
      "command": "uvx",
      "args": [
        "markdown-vault-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "MARKDOWN_VAULT_MCP_CLIENT_TOKEN": "<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>",
        "MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN": "<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>",
        "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<MARKDOWN_VAULT_MCP_GIT_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>",
        "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "markdown-vault-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "markdown-vault-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "MARKDOWN_VAULT_MCP_CLIENT_TOKEN": "<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>",
        "MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN": "<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>",
        "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<MARKDOWN_VAULT_MCP_GIT_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>",
        "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "markdown-vault-mcp": {
      "command": "uvx",
      "args": [
        "markdown-vault-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "MARKDOWN_VAULT_MCP_CLIENT_TOKEN": "<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>",
        "MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN": "<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>",
        "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<MARKDOWN_VAULT_MCP_GIT_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>",
        "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "markdown-vault-mcp": {
      "command": "uvx",
      "args": [
        "markdown-vault-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<OPENAI_API_KEY>",
        "VOYAGE_API_KEY": "<VOYAGE_API_KEY>",
        "MARKDOWN_VAULT_MCP_CLIENT_TOKEN": "<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>",
        "MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN": "<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>",
        "MARKDOWN_VAULT_MCP_GIT_TOKEN": "<MARKDOWN_VAULT_MCP_GIT_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET": "<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>",
        "MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN": "<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>",
        "MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY": "<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>"
      }
    }
  }
}

Configuration

  • MARKDOWN_VAULT_MCP_KV_STORE_URLPersistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` (with a warning) on a host where that directory is not usable.
  • MARKDOWN_VAULT_MCP_TOOLS_ALLOWComma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`.
  • MARKDOWN_VAULT_MCP_TOOLS_DENYComma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`.
  • MARKDOWN_VAULT_MCP_SERVER_NAMERename this server instance; defaults to the project name.
  • MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTIONConcise routing context that distinguishes this deployment's material or responsibility.
  • MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRADeployment-specific behavioral policy added to the generated MCP instructions.
  • MARKDOWN_VAULT_MCP_INSTRUCTIONSLegacy: replaces all generated MCP instructions (deprecated; use _INSTANCE_DESCRIPTION for routing and _INSTRUCTIONS_EXTRA for policy).
  • MARKDOWN_VAULT_MCP_LOG_LEVELLog level for every logger in the process, FastMCP's included (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. The unprefixed FASTMCP_LOG_LEVEL still works for one major version and logs a deprecation warning.
  • MARKDOWN_VAULT_MCP_LOG_FORMATLog rendering. rich is one colour event key=value line per record, for a terminal; json is one JSON object per record, for a collector. Unset picks rich when stderr is a terminal and json everywhere else, so a container or journald gets JSON with no configuration.
  • OLLAMA_HOSTOllama server URL for the ollama embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the Ollama ecosystem convention.
  • OPENAI_API_KEYOpenAI API key for the openai embedding provider, and the fallback key for the summarize tool when MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY is unset. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OpenAI ecosystem convention.
  • VOYAGE_API_KEYVoyage AI API key for the voyage embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OPENAI_API_KEY / OLLAMA_HOST convention. Setting it never auto-selects the provider; choose it explicitly with MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=voyage.
  • OPENAI_BASE_URLBare fallback for MARKDOWN_VAULT_MCP_OPENAI_BASE_URL (embeddings). For the summarize tool it only routes traffic when an API key already enables the feature; it never enables summarize by itself.
  • OPENAI_EMBEDDING_MODELBare fallback for MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL.
  • MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_SMaximum seconds an index-backed tool or resource waits for the FTS index to become queryable during a cold-start background build before raising IndexUnavailableError(reason="timeout"). Increase for large vaults.
  • MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_SMaximum seconds an index-querying read tool waits for the IndexWriter to drain when called with wait_for_pending_writes=true. On timeout the tool answers from the current index and reports index_stale=true in the response _meta.
  • MARKDOWN_VAULT_MCP_SERVER_URLHosted MCP endpoint for CLI reads. The explicit server option overrides it. Local mode bypasses it.
  • MARKDOWN_VAULT_MCP_CLIENT_CONFIGClient TOML profile path; defaults to XDG_CONFIG_HOME/markdown-vault-mcp/client.toml.
  • MARKDOWN_VAULT_MCP_CLIENT_TOKENOptional CLI bearer token. A nonempty value overrides the profile-selected token environment source; an empty value leaves that source in effect. Never stored in client TOML.
  • MARKDOWN_VAULT_MCP_SOURCE_DIRPath to the markdown vault directory. When it does not exist, or the server cannot access it, the server starts but every tool fails with a message saying which until it is fixed (managed git mode clones into it). Symbolic links inside the vault are followed on Python 3.13+.
  • MARKDOWN_VAULT_MCP_READ_ONLYSet to true to hide the write tools (write, edit, append, delete, rename, move_folder, fetch, git_sync, the okf_* tools, create_upload_link) and serve a search-only vault.
  • MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTINGRefuse a write that would overwrite an existing file when no if_match etag is supplied. Deliberate replacement still works: read the file first, then pass if_match. Unaffected: edit, append, delete, rename. Set to false to allow blind overwrites.
  • MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKSSet to true to have write, edit and append list, under unresolved_links, the target of each link the call added that get_broken_links reports. Links the note already held are left out. Off by default, leaving those responses unchanged.
  • MARKDOWN_VAULT_MCP_DISABLE_APPS_UIHide the MCP Apps UI tools (browse_vault, show_context) from the tool listing for clients that do not render MCP Apps panels.
  • MARKDOWN_VAULT_MCP_INDEX_PATHPath to the SQLite FTS5 index file; unset keeps the index in memory. Set it for persistence across restarts.
  • MARKDOWN_VAULT_MCP_STATE_PATHPath to the change-tracking state file. Defaults to INDEX_PATH plus .state.json (index.db.state.json beside index.db); without INDEX_PATH the state is kept in memory. Never written into the vault by default.
  • MARKDOWN_VAULT_MCP_EMBEDDINGS_PATHBase path for the embeddings files. Defaults beside INDEX_PATH (index-db-embeddings.sqlite3 beside index.db, or index-db-embeddings.v2.json and the matrix it names with EMBEDDING_STORE=numpy; the first build copies in the vectors a release's sidecar there holds, then leaves it alone); without INDEX_PATH the vectors are kept in memory and rebuilt at each start. Setting it also lets the provider be auto-detected.
  • MARKDOWN_VAULT_MCP_EMBEDDING_STOREWhere embeddings are stored. 'sqlite' (the default) keeps them in one SQLite database beside the index (index-db-embeddings.sqlite3), each change written durably on its own; 'numpy' keeps them in files there and rewrites them all on each save. Without INDEX_PATH or EMBEDDINGS_PATH both keep them in memory. 'postgres' keeps them in a PostgreSQL schema with pgvector (EMBEDDING_POSTGRES_DSN and EMBEDDING_POSTGRES_SCHEMA; the postgres extra).
  • MARKDOWN_VAULT_MCP_EMBEDDING_SEARCHHow semantic search reads the embeddings. 'resident' holds them all in memory, the fastest; 'streamed' keeps none in memory and reads them from the store in batches for each search, slower as the vault grows. 'streamed' needs EMBEDDING_STORE=sqlite or postgres, and postgres is always streamed; vectors kept in memory (no INDEX_PATH or EMBEDDINGS_PATH) are always resident. Unset, it is the store's default: 'streamed' with sqlite and postgres, 'resident' with numpy.
  • MARKDOWN_VAULT_MCP_EMBEDDING_SEARCH_WORKSPACE_MBWith EMBEDDING_STORE=sqlite and EMBEDDING_SEARCH=streamed, the embeddings one batch of a search may hold, in MiB (at least 1). It bounds the search's working memory, not the process's; postgres scores in the database and does not use it.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSNWith EMBEDDING_STORE=postgres, the libpq connection string or URI of the database holding the embeddings. A secret: never logged or shown. The password may instead come from PGPASSWORD or a .pgpass file.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_SCHEMAWith EMBEDDING_STORE=postgres, the schema this vault's embeddings live in: one schema per vault, created by the operator. The vault creates only its own tables there.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_POOL_SIZEWith EMBEDDING_STORE=postgres, the most connections the store opens (at least 1).
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_STATEMENT_TIMEOUT_SWith EMBEDDING_STORE=postgres, the longest one query may run, in seconds (0 sets none; at most 2147483.647). The bulk write of a full rebuild is never limited.
  • MARKDOWN_VAULT_MCP_INDEXED_FIELDSComma-separated frontmatter fields promoted to the tag index for structured filtering. Changing it cold-rebuilds the index once on next startup; SEARCHABLE_FIELDS inherits this value when unset.
  • MARKDOWN_VAULT_MCP_REQUIRED_FIELDSComma-separated frontmatter fields required on every document; documents missing any are excluded from the index.
  • MARKDOWN_VAULT_MCP_EXCLUDEComma-separated glob patterns excluded from scanning, e.g. .obsidian/**,.trash/**.
  • MARKDOWN_VAULT_MCP_TITLE_FIELDFrontmatter field used as the document title (falls back to title, the first H1, then the filename). Changing it cold-rebuilds the index once on next startup.
  • MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDSComma-separated frontmatter fields whose text values become keyword-searchable and enrich first-chunk embeddings. Inherits INDEXED_FIELDS when unset; the sentinel none means filterable but not searchable. Changing it cold-rebuilds the index and re-embeds once on next startup.
  • MARKDOWN_VAULT_MCP_TEMPLATES_FOLDERRelative folder where note templates live (used by the create_from_template prompt).
  • MARKDOWN_VAULT_MCP_PROMPTS_FOLDERDirectory of .md prompt files that extend or override built-in prompts; a relative path is resolved against SOURCE_DIR.
  • MARKDOWN_VAULT_MCP_CONVENTIONS_FILEFilename of the per-folder conventions files surfaced to clients at write time (bare .md filename without glob characters). Set to none to disable folder conventions.
  • MARKDOWN_VAULT_MCP_OKF_MODEOKF (Open Knowledge Format) read semantics. With auto (the default), read annotations switch on when the vault declares an OKF version in its root index.md. Use off to disable OKF semantics entirely, or on to force them for an undeclared vault. Annotations are read-only; write behavior is never affected.
  • MARKDOWN_VAULT_MCP_OKF_WRITEOKF (Open Knowledge Format) enforced write layer. When true on an OKF-active vault, the server stamps generated provenance on each write and clears any verified attestation when a note's content changes. It also keeps each written folder's log.md and index.md current, and exposes the okf_verify tool. Requires OKF_MODE to be auto or on (a true value with OKF_MODE=off is a config error). Off by default.
  • MARKDOWN_VAULT_MCP_OKF_VERIFYHow the okf_verify tool attributes a human review. This applies only when OKF_WRITE is on, which gates the tool. With elicit (the default), okf_verify asks the human to confirm the review through an MCP elicitation, then records the attestation only on an affirmative reply. It fails closed when the client cannot elicit or the human declines, so a model holding the human's token cannot self-attest. Set trust-auth instead to attribute to a token's sub claim with no confirmation; it rejects static bearer credentials, other client-ID-only identities, and OAuth tokens the issuer marks as an application's. This is safe only when the sole caller is a human-driven UI. Set off to hide the tool, leaving attestation to external tooling. A non-default value with OKF_WRITE off is a config error.
  • MARKDOWN_VAULT_MCP_SERVICE_SUBJECTSComma-separated token sub values that belong to applications, not people. A caller whose sub is listed is a service: its OKF writes stamp the tool actor instead of human:<sub>, and okf_verify records its review as local (elicit) or refuses it (trust-auth). Entries match the token's sub exactly. Use it for issuers whose client-credentials tokens carry nothing that marks them as an application's, such as a Keycloak, authentik or Zitadel service account; list that account's sub (for Keycloak, the service-account user's ID, not its name).
  • MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONSComma-separated allowed attachment extensions (e.g. pdf,png,jpg); case and a leading dot are ignored, so PDF and .pdf name the same type. Use * to allow every non-markdown file. Unset selects the built-in allowlist. A link whose target has a listed extension is not part of the link graph; changing the list rebuilds the index once.
  • MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MBMaximum attachment size in MB returned by read / accepted by write; 0 disables the limit.
  • MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTESMaximum bytes returned by a full-document read of a note; use `read(path, section=…)` for partial reads. 0 disables the limit.
  • MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODEMode used when a search call omits 'mode': auto, keyword, semantic, or hybrid. The default 'auto' picks hybrid when embeddings are configured and keyword when they are not. Pin 'keyword' to keep unqualified searches off the embedding provider (each hybrid or semantic search embeds the query, which costs an API call on a metered provider). A configured semantic/hybrid default also degrades to keyword without embeddings, so no setting can make a vault unsearchable; an explicit mode= argument is never downgraded.
  • MARKDOWN_VAULT_MCP_CHUNKS_PER_FILEMaximum chunks returned per document in search results.
  • MARKDOWN_VAULT_MCP_SNIPPET_WORDSWidth of the snippet window (words) in search results; 0 returns full chunk content.
  • MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHADown-weights longer chunks in ranking: score / (1 + alpha * log(chunk_count)).
  • MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDSWord cap per chunk; the adaptive chunker splits at deeper heading levels, then paragraph/word boundaries, to respect it. Match it to the embedding model's context. A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARSCharacter cap enforced alongside MAX_CHUNK_WORDS to bound token-dense chunks. Unset derives min(1500, model context * 2.8). Set a positive value for an exact cap, or -1 to scale with the model's full context (can exhaust memory on long-context models). A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDSWords of overlap between adjacent budget-split fragments of the same heading section (0 disables). A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_FOLDER_WEIGHTSFolder-prefix score multipliers (`prefix:weight` pairs, comma-separated, weights > 0) applied to all search modes; the deepest matching prefix wins (sessions:0.5 demotes sessions/**).
  • MARKDOWN_VAULT_MCP_FTS_WEIGHTSPer-column BM25 weights (`column:weight` pairs, comma-separated, weights >= 0) for keyword ranking. Columns: path, title, folder, heading, content, summary.
  • MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDEREmbedding provider: openai, voyage, ollama, or fastembed; setting it turns on search by meaning. Unset auto-detects from the environment (never voyage), but only when EMBEDDINGS_PATH is set or EMBEDDING_STORE=postgres. Any OpenAI-compatible endpoint works with openai plus OPENAI_BASE_URL; see the embeddings guide.
  • MARKDOWN_VAULT_MCP_OLLAMA_MODELOllama embedding model name.
  • MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLYForce Ollama to embed on CPU only.
  • MARKDOWN_VAULT_MCP_VOYAGE_MODELVoyage AI embedding model name.
  • MARKDOWN_VAULT_MCP_OPENAI_BASE_URLOpenAI-compatible API base URL for embeddings; the bare OPENAI_BASE_URL is honoured as a fallback.
  • MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODELOpenAI-compatible embedding model name; the bare OPENAI_EMBEDDING_MODEL is honoured as a fallback.
  • MARKDOWN_VAULT_MCP_FASTEMBED_MODELFastEmbed model name.
  • MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIRFastEmbed model cache directory (in Docker, stored under /data/state/fastembed).
  • MARKDOWN_VAULT_MCP_EMBED_CONTEXTEnrich embedding input with the note title, chunk heading, and (first chunk) searchable-field values. Flipping it re-embeds the whole vault once on next startup.
  • MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_SPer-request wall-clock budget in seconds for a single embedding HTTP call (OpenAI/Ollama). The local FastEmbed backend runs in-process with no network call and ignores this. CPU-only or large-model workloads may need 60-120 s; raise this if batches time out.
  • MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZENumber of chunks sent per embedding request. Smaller batches shorten each request (useful under a tight timeout on slow models) at the cost of more round-trips.
  • MARKDOWN_VAULT_MCP_GIT_TOKENToken/password for HTTPS git auth; remotes must be HTTPS when set.
  • MARKDOWN_VAULT_MCP_GIT_REPO_URLHTTPS remote URL for managed git mode: the server clones into an empty SOURCE_DIR on startup (or validates an existing origin) and enables the pull loop, auto-commit, and deferred push.
  • MARKDOWN_VAULT_MCP_GIT_USERNAMEUsername for HTTPS git auth prompts (x-access-token for GitHub, oauth2 for GitLab, the account name for Bitbucket).
  • MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_SSeconds between git fetch + fast-forward update attempts; 0 disables periodic pull.
  • MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_SSeconds of write-idle time before pushing; 0 pushes only on shutdown.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_NAMEGit committer name for auto-commits, and the author name too unless an OIDC claim supplies one; set this in Docker where git config user.name is empty.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAILGit committer email for auto-commits, and the author email too unless an OIDC claim supplies one.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIMOIDC claim key used as the commit author name (e.g. name) when an OIDC token is present; the committer stays GIT_COMMIT_NAME. The claim is resolved when the tool call arrives and carried to the background commit, so it applies on every write. A configured claim the token does not carry is reported once at WARNING and the static identity is used.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIMOIDC claim key used as the commit author email (e.g. email) when an OIDC token is present; the committer stays GIT_COMMIT_EMAIL. Resolved and carried the same way as the name claim.
  • MARKDOWN_VAULT_MCP_GIT_LFSRun git lfs pull on startup to fetch LFS-tracked attachments; set to false for repos without LFS.
  • MARKDOWN_VAULT_MCP_FILE_WATCHERWatch the vault for external filesystem changes; auto-disabled when git pull is active or a webhook can deliver (HTTP/SSE transports only). Requires the file-watcher extra.
  • MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_SSeconds of quiet after the last filesystem event before reindexing.
  • MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOORKeep the non-recursive watch on the vault root; set false to register zero source-dir-rooted FSEvents streams (avoids repeated macOS access prompts on a home-rooted vault) at the cost of root-level files relying on scans.
  • MARKDOWN_VAULT_MCP_BOOT_REINDEXReconcile offline changes at startup by reindexing once the initial build completes. Set false on a large vault to start without paying a full filesystem scan per server start; changes made while no server was running are then invisible until a reindex runs (the reindex tool, or 'markdown-vault-mcp admin reindex'). `get_index_status` reports `offline_changes` as `not_reconciled` until the server itself runs one; a reindex from the command line updates the index but not that status. Note that `index_stale` reports writer idleness, not agreement with disk, so it reads false while the index may still differ from the vault.
  • MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRETShared secret for the GitHub push-event webhook; when set, mounts POST /github-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events.
  • MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKENSigning token for the GitLab push-event webhook (GitLab 19.0+); when set, mounts POST /gitlab-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. GitLab generates this value; copy the `whsec_` token it shows under Generate signing token rather than inventing one. Deliveries are authenticated by HMAC-SHA256 over the webhook id, timestamp and body, and a delivery older than 5 minutes is rejected.
  • MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKENSecret token for the GitLab push-event webhook, GitLab's plain-text form and the only one below 19.0; also mounts POST /gitlab-webhook. It proves nothing about the body and cannot expire, so prefer the signing token where the GitLab version offers it. Setting both accepts either, which is how an existing webhook migrates.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDERSummarization backend (only openai is recognised). Unset auto-detects: the backend activates when credentials or an explicit endpoint are present.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEYAPI key for the OpenAI-compatible summarize endpoint; the bare OPENAI_API_KEY is honoured as a fallback. Unset works for keyless local endpoints (Ollama).
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URLOpenAI-compatible endpoint base URL for the summarize tool; setting it enables the tool even without an API key. The bare OPENAI_BASE_URL routes traffic only when a key already enables the feature.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODELChat model id used for summaries.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENSUpper bound on generated tokens per summarize call; on reasoning models this budget also covers internal reasoning tokens.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTESCap on the number of notes summarised in one call (subtree expansion truncates to this many).
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARSAggregate cap on note characters sent to the model in one call; excess is truncated with a flag on the result.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUTPer-request wall-clock budget in seconds for a single summarize backend call; keep it below the MCP client's request timeout so the server-side error wins the race.
  • MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_SLink lifetime in seconds when the caller requests no explicit TTL.
  • MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_SCeiling in seconds a caller-requested link TTL is clamped to.
  • MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_SPost-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.
  • MARKDOWN_VAULT_MCP_TRANSFER_LEASE_SCrashed-handler reclaim window in seconds for an in-flight reservation.
  • MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTESMaximum size in bytes of a single upload.
  • MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_SSeconds a long-running tool call may run in the foreground before it is promoted to a background job and a job handle is returned instead.
  • MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_SSeconds a background-job record (working or finished) is retained for polling before it expires from the store.
  • MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECTMaximum live background jobs per calling subject; further promotions are rejected until older records expire.
  • MARKDOWN_VAULT_MCP_SHUTDOWN_GRACE_SSeconds SIGTERM may spend draining in-flight requests before the HTTP server exits. Keep it at or below the termination grace period the orchestrator allows. `0` drops in-flight requests immediately.
  • MARKDOWN_VAULT_MCP_BASE_URLPublic base URL of the deployed server, for example `https://mcp.example.com`. Required for OIDC. Also the fallback source of the MCP Apps domain when `app_domain` is unset.
  • MARKDOWN_VAULT_MCP_BEARER_TOKENSingle shared bearer token; enables bearer auth unless `bearer_tokens_file` is set, which takes precedence.
  • MARKDOWN_VAULT_MCP_OIDC_CONFIG_URLOIDC discovery document URL, for example `https://auth.example.com/.well-known/openid-configuration`.
  • MARKDOWN_VAULT_MCP_OIDC_CLIENT_IDOIDC client identifier registered with the provider.
  • MARKDOWN_VAULT_MCP_OIDC_CLIENT_SECRETOIDC client secret registered with the provider.
  • MARKDOWN_VAULT_MCP_OIDC_AUDIENCEExpected `aud` claim; tokens issued for another audience are rejected.
  • MARKDOWN_VAULT_MCP_OIDC_REQUIRED_SCOPESScopes a caller must present, space- or comma-separated. Defaults to `openid` in oidc-proxy mode.
  • MARKDOWN_VAULT_MCP_OIDC_ADVERTISED_SCOPESScopes advertised to MCP clients in protected-resource metadata, space- or comma-separated. Overrides the default `openid offline_access`; `oidc_required_scopes` is always added on top. Set this when the registered client is not permitted `offline_access`, or to have clients request extra claim scopes (such as `groups`) without also requiring them in every token.
  • MARKDOWN_VAULT_MCP_OIDC_JWT_SIGNING_KEYSigning key for issued tokens; used in oidc-proxy mode only. When unset, the key is derived deterministically from `oidc_client_secret`, so tokens survive a restart. Rotating that secret then invalidates every issued token. Set this explicitly to decouple token validity from secret rotation. Generate with `openssl rand -hex 32`.
  • MARKDOWN_VAULT_MCP_OIDC_VERIFY_ACCESS_TOKENValidate the access token instead of the id token.
  • MARKDOWN_VAULT_MCP_KV_STORE_URLPersistent-state backend URL shared by every pvl-core subsystem that needs state. `memory://` is in-process and lost on restart; `file:///path` persists on one server; `redis://`, `dynamodb://` and `mongodb://` each need their matching extra. When unset, defaults to `file:///data/state` (the volume family Docker images mount), or to `memory://` (with a warning) on a host where that directory is not usable.
  • MARKDOWN_VAULT_MCP_APP_DOMAINMCP Apps iframe domain, used for CSP sandboxing. Overrides the host derived from `base_url`.
  • MARKDOWN_VAULT_MCP_TOOLS_ALLOWComma-separated explicit tool names this instance exposes; every other tool is hidden from listings and cannot be invoked. Names matching no registered tool are inert. Mutually exclusive with `tools_deny`. Takes effect through `apply_tool_visibility`.
  • MARKDOWN_VAULT_MCP_TOOLS_DENYComma-separated explicit tool names hidden from this instance (absent from listings, cannot be invoked). Names matching no registered tool are inert. Mutually exclusive with `tools_allow`. Takes effect through `apply_tool_visibility`.
  • MARKDOWN_VAULT_MCP_AUTH_MODEExplicit auth-mode override, accepting `remote` or `oidc-proxy` (case- and whitespace-insensitive). When unset the mode is auto-detected from which auth variables are set; the override exists because having all four OIDC variables set is ambiguous between those two modes. Other values are ignored with a warning.
  • MARKDOWN_VAULT_MCP_BEARER_TOKENS_FILEPath to a TOML file mapping bearer tokens to subjects; overrides the single-token `bearer_token` mode.
  • MARKDOWN_VAULT_MCP_BEARER_DEFAULT_SUBJECTSubject assigned to the single-token bearer mode; ignored when `bearer_tokens_file` is set, since mapped mode carries per-token subjects.
  • MARKDOWN_VAULT_MCP_SERVER_NAMERename this server instance; defaults to the project name.
  • MARKDOWN_VAULT_MCP_INSTANCE_DESCRIPTIONConcise routing context that distinguishes this deployment's material or responsibility.
  • MARKDOWN_VAULT_MCP_INSTRUCTIONS_EXTRADeployment-specific behavioral policy added to the generated MCP instructions.
  • MARKDOWN_VAULT_MCP_INSTRUCTIONSLegacy: replaces all generated MCP instructions (deprecated; use _INSTANCE_DESCRIPTION for routing and _INSTRUCTIONS_EXTRA for policy).
  • MARKDOWN_VAULT_MCP_HTTP_PATHMount path for the MCP endpoint; the health routes derive their prefix from it.
  • MARKDOWN_VAULT_MCP_HEALTH_DETAILHow much the unauthenticated /health and /health/ready bodies say: status, standard (adds name, version and per-check verdicts), or full (adds redacted reasons; trusted networks only).
  • PUIDRun the server process as this UID; the container entrypoint reassigns ownership of writable paths to match.
  • PGIDRun the server process as this GID; pair with PUID to match the owner of a mounted volume.
  • MARKDOWN_VAULT_MCP_LOG_LEVELLog level for every logger in the process, FastMCP's included (DEBUG / INFO / WARNING / ERROR / CRITICAL). The -v CLI flag overrides to DEBUG. The unprefixed FASTMCP_LOG_LEVEL still works for one major version and logs a deprecation warning.
  • MARKDOWN_VAULT_MCP_LOG_FORMATLog rendering. rich is one colour event key=value line per record, for a terminal; json is one JSON object per record, for a collector. Unset picks rich when stderr is a terminal and json everywhere else, so a container or journald gets JSON with no configuration.
  • OLLAMA_HOSTOllama server URL for the ollama embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the Ollama ecosystem convention.
  • OPENAI_API_KEYOpenAI API key for the openai embedding provider, and the fallback key for the summarize tool when MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY is unset. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OpenAI ecosystem convention.
  • VOYAGE_API_KEYVoyage AI API key for the voyage embedding provider. Bare (not MARKDOWN_VAULT_MCP_-prefixed), matching the OPENAI_API_KEY / OLLAMA_HOST convention. Setting it never auto-selects the provider; choose it explicitly with MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDER=voyage.
  • OPENAI_BASE_URLBare fallback for MARKDOWN_VAULT_MCP_OPENAI_BASE_URL (embeddings). For the summarize tool it only routes traffic when an API key already enables the feature; it never enables summarize by itself.
  • OPENAI_EMBEDDING_MODELBare fallback for MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODEL.
  • MARKDOWN_VAULT_MCP_BUILD_TIMEOUT_SMaximum seconds an index-backed tool or resource waits for the FTS index to become queryable during a cold-start background build before raising IndexUnavailableError(reason="timeout"). Increase for large vaults.
  • MARKDOWN_VAULT_MCP_DRAIN_TIMEOUT_SMaximum seconds an index-querying read tool waits for the IndexWriter to drain when called with wait_for_pending_writes=true. On timeout the tool answers from the current index and reports index_stale=true in the response _meta.
  • MARKDOWN_VAULT_MCP_SERVER_URLHosted MCP endpoint for CLI reads. The explicit server option overrides it. Local mode bypasses it.
  • MARKDOWN_VAULT_MCP_CLIENT_CONFIGClient TOML profile path; defaults to XDG_CONFIG_HOME/markdown-vault-mcp/client.toml.
  • MARKDOWN_VAULT_MCP_CLIENT_TOKENOptional CLI bearer token. A nonempty value overrides the profile-selected token environment source; an empty value leaves that source in effect. Never stored in client TOML.
  • MARKDOWN_VAULT_MCP_SOURCE_DIRPath to the markdown vault directory. When it does not exist, or the server cannot access it, the server starts but every tool fails with a message saying which until it is fixed (managed git mode clones into it). Symbolic links inside the vault are followed on Python 3.13+.
  • MARKDOWN_VAULT_MCP_READ_ONLYSet to true to hide the write tools (write, edit, append, delete, rename, move_folder, fetch, git_sync, the okf_* tools, create_upload_link) and serve a search-only vault.
  • MARKDOWN_VAULT_MCP_WRITE_PROTECT_EXISTINGRefuse a write that would overwrite an existing file when no if_match etag is supplied. Deliberate replacement still works: read the file first, then pass if_match. Unaffected: edit, append, delete, rename. Set to false to allow blind overwrites.
  • MARKDOWN_VAULT_MCP_REPORT_UNRESOLVED_LINKSSet to true to have write, edit and append list, under unresolved_links, the target of each link the call added that get_broken_links reports. Links the note already held are left out. Off by default, leaving those responses unchanged.
  • MARKDOWN_VAULT_MCP_DISABLE_APPS_UIHide the MCP Apps UI tools (browse_vault, show_context) from the tool listing for clients that do not render MCP Apps panels.
  • MARKDOWN_VAULT_MCP_INDEX_PATHPath to the SQLite FTS5 index file; unset keeps the index in memory. Set it for persistence across restarts.
  • MARKDOWN_VAULT_MCP_STATE_PATHPath to the change-tracking state file. Defaults to INDEX_PATH plus .state.json (index.db.state.json beside index.db); without INDEX_PATH the state is kept in memory. Never written into the vault by default.
  • MARKDOWN_VAULT_MCP_EMBEDDINGS_PATHBase path for the embeddings files. Defaults beside INDEX_PATH (index-db-embeddings.sqlite3 beside index.db, or index-db-embeddings.v2.json and the matrix it names with EMBEDDING_STORE=numpy; the first build copies in the vectors a release's sidecar there holds, then leaves it alone); without INDEX_PATH the vectors are kept in memory and rebuilt at each start. Setting it also lets the provider be auto-detected.
  • MARKDOWN_VAULT_MCP_EMBEDDING_STOREWhere embeddings are stored. 'sqlite' (the default) keeps them in one SQLite database beside the index (index-db-embeddings.sqlite3), each change written durably on its own; 'numpy' keeps them in files there and rewrites them all on each save. Without INDEX_PATH or EMBEDDINGS_PATH both keep them in memory. 'postgres' keeps them in a PostgreSQL schema with pgvector (EMBEDDING_POSTGRES_DSN and EMBEDDING_POSTGRES_SCHEMA; the postgres extra).
  • MARKDOWN_VAULT_MCP_EMBEDDING_SEARCHHow semantic search reads the embeddings. 'resident' holds them all in memory, the fastest; 'streamed' keeps none in memory and reads them from the store in batches for each search, slower as the vault grows. 'streamed' needs EMBEDDING_STORE=sqlite or postgres, and postgres is always streamed; vectors kept in memory (no INDEX_PATH or EMBEDDINGS_PATH) are always resident. Unset, it is the store's default: 'streamed' with sqlite and postgres, 'resident' with numpy.
  • MARKDOWN_VAULT_MCP_EMBEDDING_SEARCH_WORKSPACE_MBWith EMBEDDING_STORE=sqlite and EMBEDDING_SEARCH=streamed, the embeddings one batch of a search may hold, in MiB (at least 1). It bounds the search's working memory, not the process's; postgres scores in the database and does not use it.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSNWith EMBEDDING_STORE=postgres, the libpq connection string or URI of the database holding the embeddings. A secret: never logged or shown. The password may instead come from PGPASSWORD or a .pgpass file.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_SCHEMAWith EMBEDDING_STORE=postgres, the schema this vault's embeddings live in: one schema per vault, created by the operator. The vault creates only its own tables there.
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_POOL_SIZEWith EMBEDDING_STORE=postgres, the most connections the store opens (at least 1).
  • MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_STATEMENT_TIMEOUT_SWith EMBEDDING_STORE=postgres, the longest one query may run, in seconds (0 sets none; at most 2147483.647). The bulk write of a full rebuild is never limited.
  • MARKDOWN_VAULT_MCP_INDEXED_FIELDSComma-separated frontmatter fields promoted to the tag index for structured filtering. Changing it cold-rebuilds the index once on next startup; SEARCHABLE_FIELDS inherits this value when unset.
  • MARKDOWN_VAULT_MCP_REQUIRED_FIELDSComma-separated frontmatter fields required on every document; documents missing any are excluded from the index.
  • MARKDOWN_VAULT_MCP_EXCLUDEComma-separated glob patterns excluded from scanning, e.g. .obsidian/**,.trash/**.
  • MARKDOWN_VAULT_MCP_TITLE_FIELDFrontmatter field used as the document title (falls back to title, the first H1, then the filename). Changing it cold-rebuilds the index once on next startup.
  • MARKDOWN_VAULT_MCP_SEARCHABLE_FIELDSComma-separated frontmatter fields whose text values become keyword-searchable and enrich first-chunk embeddings. Inherits INDEXED_FIELDS when unset; the sentinel none means filterable but not searchable. Changing it cold-rebuilds the index and re-embeds once on next startup.
  • MARKDOWN_VAULT_MCP_TEMPLATES_FOLDERRelative folder where note templates live (used by the create_from_template prompt).
  • MARKDOWN_VAULT_MCP_PROMPTS_FOLDERDirectory of .md prompt files that extend or override built-in prompts; a relative path is resolved against SOURCE_DIR.
  • MARKDOWN_VAULT_MCP_CONVENTIONS_FILEFilename of the per-folder conventions files surfaced to clients at write time (bare .md filename without glob characters). Set to none to disable folder conventions.
  • MARKDOWN_VAULT_MCP_OKF_MODEOKF (Open Knowledge Format) read semantics. With auto (the default), read annotations switch on when the vault declares an OKF version in its root index.md. Use off to disable OKF semantics entirely, or on to force them for an undeclared vault. Annotations are read-only; write behavior is never affected.
  • MARKDOWN_VAULT_MCP_OKF_WRITEOKF (Open Knowledge Format) enforced write layer. When true on an OKF-active vault, the server stamps generated provenance on each write and clears any verified attestation when a note's content changes. It also keeps each written folder's log.md and index.md current, and exposes the okf_verify tool. Requires OKF_MODE to be auto or on (a true value with OKF_MODE=off is a config error). Off by default.
  • MARKDOWN_VAULT_MCP_OKF_VERIFYHow the okf_verify tool attributes a human review. This applies only when OKF_WRITE is on, which gates the tool. With elicit (the default), okf_verify asks the human to confirm the review through an MCP elicitation, then records the attestation only on an affirmative reply. It fails closed when the client cannot elicit or the human declines, so a model holding the human's token cannot self-attest. Set trust-auth instead to attribute to a token's sub claim with no confirmation; it rejects static bearer credentials, other client-ID-only identities, and OAuth tokens the issuer marks as an application's. This is safe only when the sole caller is a human-driven UI. Set off to hide the tool, leaving attestation to external tooling. A non-default value with OKF_WRITE off is a config error.
  • MARKDOWN_VAULT_MCP_SERVICE_SUBJECTSComma-separated token sub values that belong to applications, not people. A caller whose sub is listed is a service: its OKF writes stamp the tool actor instead of human:<sub>, and okf_verify records its review as local (elicit) or refuses it (trust-auth). Entries match the token's sub exactly. Use it for issuers whose client-credentials tokens carry nothing that marks them as an application's, such as a Keycloak, authentik or Zitadel service account; list that account's sub (for Keycloak, the service-account user's ID, not its name).
  • MARKDOWN_VAULT_MCP_ATTACHMENT_EXTENSIONSComma-separated allowed attachment extensions (e.g. pdf,png,jpg); case and a leading dot are ignored, so PDF and .pdf name the same type. Use * to allow every non-markdown file. Unset selects the built-in allowlist. A link whose target has a listed extension is not part of the link graph; changing the list rebuilds the index once.
  • MARKDOWN_VAULT_MCP_MAX_ATTACHMENT_SIZE_MBMaximum attachment size in MB returned by read / accepted by write; 0 disables the limit.
  • MARKDOWN_VAULT_MCP_MAX_NOTE_READ_BYTESMaximum bytes returned by a full-document read of a note; use `read(path, section=…)` for partial reads. 0 disables the limit.
  • MARKDOWN_VAULT_MCP_DEFAULT_SEARCH_MODEMode used when a search call omits 'mode': auto, keyword, semantic, or hybrid. The default 'auto' picks hybrid when embeddings are configured and keyword when they are not. Pin 'keyword' to keep unqualified searches off the embedding provider (each hybrid or semantic search embeds the query, which costs an API call on a metered provider). A configured semantic/hybrid default also degrades to keyword without embeddings, so no setting can make a vault unsearchable; an explicit mode= argument is never downgraded.
  • MARKDOWN_VAULT_MCP_CHUNKS_PER_FILEMaximum chunks returned per document in search results.
  • MARKDOWN_VAULT_MCP_SNIPPET_WORDSWidth of the snippet window (words) in search results; 0 returns full chunk content.
  • MARKDOWN_VAULT_MCP_LENGTH_DOWNWEIGHT_ALPHADown-weights longer chunks in ranking: score / (1 + alpha * log(chunk_count)).
  • MARKDOWN_VAULT_MCP_MAX_CHUNK_WORDSWord cap per chunk; the adaptive chunker splits at deeper heading levels, then paragraph/word boundaries, to respect it. Match it to the embedding model's context. A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_MAX_CHUNK_CHARSCharacter cap enforced alongside MAX_CHUNK_WORDS to bound token-dense chunks. Unset derives min(1500, model context * 2.8). Set a positive value for an exact cap, or -1 to scale with the model's full context (can exhaust memory on long-context models). A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_CHUNK_OVERLAP_WORDSWords of overlap between adjacent budget-split fragments of the same heading section (0 disables). A reindex applies a new value.
  • MARKDOWN_VAULT_MCP_FOLDER_WEIGHTSFolder-prefix score multipliers (`prefix:weight` pairs, comma-separated, weights > 0) applied to all search modes; the deepest matching prefix wins (sessions:0.5 demotes sessions/**).
  • MARKDOWN_VAULT_MCP_FTS_WEIGHTSPer-column BM25 weights (`column:weight` pairs, comma-separated, weights >= 0) for keyword ranking. Columns: path, title, folder, heading, content, summary.
  • MARKDOWN_VAULT_MCP_EMBEDDING_PROVIDEREmbedding provider: openai, voyage, ollama, or fastembed; setting it turns on search by meaning. Unset auto-detects from the environment (never voyage), but only when EMBEDDINGS_PATH is set or EMBEDDING_STORE=postgres. Any OpenAI-compatible endpoint works with openai plus OPENAI_BASE_URL; see the embeddings guide.
  • MARKDOWN_VAULT_MCP_OLLAMA_MODELOllama embedding model name.
  • MARKDOWN_VAULT_MCP_OLLAMA_CPU_ONLYForce Ollama to embed on CPU only.
  • MARKDOWN_VAULT_MCP_VOYAGE_MODELVoyage AI embedding model name.
  • MARKDOWN_VAULT_MCP_OPENAI_BASE_URLOpenAI-compatible API base URL for embeddings; the bare OPENAI_BASE_URL is honoured as a fallback.
  • MARKDOWN_VAULT_MCP_OPENAI_EMBEDDING_MODELOpenAI-compatible embedding model name; the bare OPENAI_EMBEDDING_MODEL is honoured as a fallback.
  • MARKDOWN_VAULT_MCP_FASTEMBED_MODELFastEmbed model name.
  • MARKDOWN_VAULT_MCP_FASTEMBED_CACHE_DIRFastEmbed model cache directory (in Docker, stored under /data/state/fastembed).
  • MARKDOWN_VAULT_MCP_EMBED_CONTEXTEnrich embedding input with the note title, chunk heading, and (first chunk) searchable-field values. Flipping it re-embeds the whole vault once on next startup.
  • MARKDOWN_VAULT_MCP_EMBED_TIMEOUT_SPer-request wall-clock budget in seconds for a single embedding HTTP call (OpenAI/Ollama). The local FastEmbed backend runs in-process with no network call and ignores this. CPU-only or large-model workloads may need 60-120 s; raise this if batches time out.
  • MARKDOWN_VAULT_MCP_EMBEDDING_BATCH_SIZENumber of chunks sent per embedding request. Smaller batches shorten each request (useful under a tight timeout on slow models) at the cost of more round-trips.
  • MARKDOWN_VAULT_MCP_GIT_TOKENToken/password for HTTPS git auth; remotes must be HTTPS when set.
  • MARKDOWN_VAULT_MCP_GIT_REPO_URLHTTPS remote URL for managed git mode: the server clones into an empty SOURCE_DIR on startup (or validates an existing origin) and enables the pull loop, auto-commit, and deferred push.
  • MARKDOWN_VAULT_MCP_GIT_USERNAMEUsername for HTTPS git auth prompts (x-access-token for GitHub, oauth2 for GitLab, the account name for Bitbucket).
  • MARKDOWN_VAULT_MCP_GIT_PULL_INTERVAL_SSeconds between git fetch + fast-forward update attempts; 0 disables periodic pull.
  • MARKDOWN_VAULT_MCP_GIT_PUSH_DELAY_SSeconds of write-idle time before pushing; 0 pushes only on shutdown.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_NAMEGit committer name for auto-commits, and the author name too unless an OIDC claim supplies one; set this in Docker where git config user.name is empty.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAILGit committer email for auto-commits, and the author email too unless an OIDC claim supplies one.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_NAME_CLAIMOIDC claim key used as the commit author name (e.g. name) when an OIDC token is present; the committer stays GIT_COMMIT_NAME. The claim is resolved when the tool call arrives and carried to the background commit, so it applies on every write. A configured claim the token does not carry is reported once at WARNING and the static identity is used.
  • MARKDOWN_VAULT_MCP_GIT_COMMIT_EMAIL_CLAIMOIDC claim key used as the commit author email (e.g. email) when an OIDC token is present; the committer stays GIT_COMMIT_EMAIL. Resolved and carried the same way as the name claim.
  • MARKDOWN_VAULT_MCP_GIT_LFSRun git lfs pull on startup to fetch LFS-tracked attachments; set to false for repos without LFS.
  • MARKDOWN_VAULT_MCP_FILE_WATCHERWatch the vault for external filesystem changes; auto-disabled when git pull is active or a webhook can deliver (HTTP/SSE transports only). Requires the file-watcher extra.
  • MARKDOWN_VAULT_MCP_FILE_WATCHER_DEBOUNCE_SSeconds of quiet after the last filesystem event before reindexing.
  • MARKDOWN_VAULT_MCP_FILE_WATCHER_ROOT_FLOORKeep the non-recursive watch on the vault root; set false to register zero source-dir-rooted FSEvents streams (avoids repeated macOS access prompts on a home-rooted vault) at the cost of root-level files relying on scans.
  • MARKDOWN_VAULT_MCP_BOOT_REINDEXReconcile offline changes at startup by reindexing once the initial build completes. Set false on a large vault to start without paying a full filesystem scan per server start; changes made while no server was running are then invisible until a reindex runs (the reindex tool, or 'markdown-vault-mcp admin reindex'). `get_index_status` reports `offline_changes` as `not_reconciled` until the server itself runs one; a reindex from the command line updates the index but not that status. Note that `index_stale` reports writer idleness, not agreement with disk, so it reads false while the index may still differ from the vault.
  • MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRETShared secret for the GitHub push-event webhook; when set, mounts POST /github-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events.
  • MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKENSigning token for the GitLab push-event webhook (GitLab 19.0+); when set, mounts POST /gitlab-webhook on HTTP/SSE transports to trigger an immediate pull + reindex on push events. GitLab generates this value; copy the `whsec_` token it shows under Generate signing token rather than inventing one. Deliveries are authenticated by HMAC-SHA256 over the webhook id, timestamp and body, and a delivery older than 5 minutes is rejected.
  • MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKENSecret token for the GitLab push-event webhook, GitLab's plain-text form and the only one below 19.0; also mounts POST /gitlab-webhook. It proves nothing about the body and cannot expire, so prefer the signing token where the GitLab version offers it. Setting both accepts either, which is how an existing webhook migrates.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_PROVIDERSummarization backend (only openai is recognised). Unset auto-detects: the backend activates when credentials or an explicit endpoint are present.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEYAPI key for the OpenAI-compatible summarize endpoint; the bare OPENAI_API_KEY is honoured as a fallback. Unset works for keyless local endpoints (Ollama).
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_BASE_URLOpenAI-compatible endpoint base URL for the summarize tool; setting it enables the tool even without an API key. The bare OPENAI_BASE_URL routes traffic only when a key already enables the feature.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_MODELChat model id used for summaries.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_TOKENSUpper bound on generated tokens per summarize call; on reasoning models this budget also covers internal reasoning tokens.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_NOTESCap on the number of notes summarised in one call (subtree expansion truncates to this many).
  • MARKDOWN_VAULT_MCP_SUMMARIZE_MAX_INPUT_CHARSAggregate cap on note characters sent to the model in one call; excess is truncated with a flag on the result.
  • MARKDOWN_VAULT_MCP_SUMMARIZE_TIMEOUTPer-request wall-clock budget in seconds for a single summarize backend call; keep it below the MCP client's request timeout so the server-side error wins the race.
  • MARKDOWN_VAULT_MCP_TRANSFER_TTL_DEFAULT_SLink lifetime in seconds when the caller requests no explicit TTL.
  • MARKDOWN_VAULT_MCP_TRANSFER_TTL_MAX_SCeiling in seconds a caller-requested link TTL is clamped to.
  • MARKDOWN_VAULT_MCP_TRANSFER_GRACE_TTL_SPost-success grace window in seconds: a served token's TTL shrinks to this so a stalled transfer can retry within it.
  • MARKDOWN_VAULT_MCP_TRANSFER_LEASE_SCrashed-handler reclaim window in seconds for an in-flight reservation.
  • MARKDOWN_VAULT_MCP_TRANSFER_MAX_UPLOAD_BYTESMaximum size in bytes of a single upload.
  • MARKDOWN_VAULT_MCP_JOBS_SOFT_DEADLINE_SSeconds a long-running tool call may run in the foreground before it is promoted to a background job and a job handle is returned instead.
  • MARKDOWN_VAULT_MCP_JOBS_RESULT_TTL_SSeconds a background-job record (working or finished) is retained for polling before it expires from the store.
  • MARKDOWN_VAULT_MCP_JOBS_MAX_PER_SUBJECTMaximum live background jobs per calling subject; further promotions are rejected until older records expire.

Tools this server provides (14)

Taken from the project documentation; the running server may differ.

read
Fetch a whole note section
write
Write a note
edit
Edit a note
append
Append to a note
delete
Delete a note
rename
Rename a note
move_folder
Move a folder
fetch
Fetch content into the vault
git_sync
Sync with Git
create_upload_link
Create an upload link
search_paths
Find literal paths or nearby ASCII spellings
query_documents
Page through indexed notes
count_documents
Count every matching note
aggregate_documents
Group the matching population into buckets

What it does

Hybrid search
Combines FTS5 keyword search with optional embedding search.
Exact queries
Pages, counts and aggregates indexed notes by frontmatter fields.
Guarded writes
Needs an etag to replace a file and can be set read-only.
Git integration
Commits writes optionally and reads back earlier revisions.
Link tools
Finds backlinks, outlinks, broken links and note-to-note paths.
Tool allow and deny lists
Hides selected tools from a given instance.

Good for

  • Let an assistant search a personal notes vault
  • Edit and append to notes with conflict protection
  • Find broken links in a knowledge base
  • Count notes by tag
  • Keep note edits under Git history

Pricing

Free

Self-hosted; embedding providers such as OpenAI bill separately if used

Prices change. Check pvliesdonk.github.io before you buy.

Markdown Vault MCP FAQ

Does it work with Obsidian?

Yes. The README says an Obsidian vault works as it is.

Which embedding providers can it use?

Ollama and OpenAI are listed; search by meaning is off until one is configured.

Can I make it read-only?

Yes, by setting MARKDOWN_VAULT_MCP_READ_ONLY=true.

Where are vectors stored?

In SQLite, files or PostgreSQL.

Is Markdown Vault MCP free?

Yes. Markdown Vault MCP is free to use.

How do I add Markdown Vault MCP to Claude Code?

Run this command in your terminal: claude mcp add markdown-vault-mcp --env OPENAI_API_KEY='<OPENAI_API_KEY>' --env VOYAGE_API_KEY='<VOYAGE_API_KEY>' --env MARKDOWN_VAULT_MCP_CLIENT_TOKEN='<MARKDOWN_VAULT_MCP_CLIENT_TOKEN>' --env MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN='<MARKDOWN_VAULT_MCP_EMBEDDING_POSTGRES_DSN>' --env MARKDOWN_VAULT_MCP_GIT_TOKEN='<MARKDOWN_VAULT_MCP_GIT_TOKEN>' --env MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET='<MARKDOWN_VAULT_MCP_GITHUB_WEBHOOK_SECRET>' --env MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN='<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SIGNING_TOKEN>' --env MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN='<MARKDOWN_VAULT_MCP_GITLAB_WEBHOOK_SECRET_TOKEN>' --env MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY='<MARKDOWN_VAULT_MCP_SUMMARIZE_OPENAI_API_KEY>' -- uvx markdown-vault-mcp

What are the best alternatives to Markdown Vault MCP?

The closest alternatives to Markdown Vault MCP are REA, Codebase Memory, XERJ, Claude Code Ultimate Guide and Nautilus Compass Memory.

Alternatives to Markdown Vault MCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  4. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  5. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  6. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools