Skip to content
MCP server

slivingdoc

Shared notes for agents and people, merged Git-style and stored in S3

Runs locallyStatus and history
Install
Pricing
Freemium
Platforms
CLI, self-hosted, Web
Runs
Locally
Version
1.3.1
Listing updated
2 days ago

About slivingdoc

slivingdoc is a freemium MCP server for knowledge and memory. It runs locally on your machine and is started by your AI client.

slivingdoc gives agents a notebook that outlives any single session. Agents and humans pull a directory of plain UTF-8 text files, edit them with ordinary file tools, then commit; concurrent edits to different lines merge, and the same line becomes a reported conflict instead of an overwrite.

Storage is either a hosted space on slivingdoc.dev or your own S3-compatible bucket that supports conditional writes. The README and site describe uses such as shared context across Claude Code and Codex, fleets of agents that each commit a report, and memory for CI jobs and sandboxes that lose their disk after every run. Access rules can mark paths read-only so instructions can be changed at runtime.

The MCP server runs over stdio via npx. The pull operation is exposed as notes_pull, with a matching CLI command. The project is MIT licensed.

Install

Run in a terminal

claude mcp add slivingdoc --env SLIVINGDOC_TOKEN='<SLIVINGDOC_TOKEN>' -- npx -y slivingdoc

Add to claude_desktop_config.json

{
  "mcpServers": {
    "slivingdoc": {
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc"
      ],
      "env": {
        "SLIVINGDOC_TOKEN": "<SLIVINGDOC_TOKEN>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "slivingdoc": {
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc"
      ],
      "env": {
        "SLIVINGDOC_TOKEN": "<SLIVINGDOC_TOKEN>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "slivingdoc": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc"
      ],
      "env": {
        "SLIVINGDOC_TOKEN": "<SLIVINGDOC_TOKEN>"
      }
    }
  }
}

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

{
  "mcpServers": {
    "slivingdoc": {
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc"
      ],
      "env": {
        "SLIVINGDOC_TOKEN": "<SLIVINGDOC_TOKEN>"
      }
    }
  }
}

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

{
  "mcpServers": {
    "slivingdoc": {
      "command": "npx",
      "args": [
        "-y",
        "slivingdoc"
      ],
      "env": {
        "SLIVINGDOC_TOKEN": "<SLIVINGDOC_TOKEN>"
      }
    }
  }
}

Configuration

  • SLIVINGDOC_TOKENAPI token from slivingdoc.dev for hosted storage; use it instead of the bucket and AWS settings, and leave AWS_ENDPOINT_URL_S3 unset.
  • SLIVINGDOC_BUCKETS3-compatible bucket that stores the shared text workspace. Not needed with SLIVINGDOC_TOKEN, which names its own space.
  • AWS_PROFILEOptional AWS profile used by the standard AWS credential chain.
  • AWS_REGIONAWS region for the bucket or S3-compatible endpoint.
  • AWS_ENDPOINT_URL_S3Optional endpoint for an S3-compatible store such as SeaweedFS.
  • SLIVINGDOC_WORKSPACE_ROOTOptional root that contains directories agents may pull and commit.

Tools this server provides (1)

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

notes_pull
Pulls the shared notebook into the server's directory, merging unpublished local edits with the accepted state.

What it does

Git-style merging
Merges non-conflicting concurrent edits and reports conflicts.
Plain text checkout
Notes are ordinary files you pull into a directory.
Your bucket or hosted
Use any S3-compatible bucket or a hosted space on slivingdoc.dev.
Path permissions
Choose where agents may read and where they may write.
MCP and CLI
The same pull and commit operations are available both ways.
Invite sharing
Hosted spaces can be shared with invite links.

Good for

  • Keep one shared context for several coding agents
  • Give CI agents memory between runs
  • Collect reports from a fleet of agents in one place
  • Change agent instructions without redeploying
  • Share notes between colleagues from the command line

Pricing

Freemium, from $1 a month

Self-hosted free; hosted free tier then $1 a month per added step

Prices change. Check slivingdoc.dev before you buy.

slivingdoc FAQ

What does hosting cost?

Free for one space with 10 MiB and 250,000 requests a month; extra spaces, storage and requests are $1 a month each step.

Can I self-host?

Yes, for free, against your own S3-compatible bucket with conditional writes.

What happens at a usage limit?

At the storage limit new commits are refused while pulls keep working; at the request limit commits are refused and reads slow down.

Are binary files supported?

No. The pricing page says text files only.

Is slivingdoc free?

slivingdoc has a free plan, with paid plans for more usage or features. Paid plans start at $1 a month.

How do I add slivingdoc to Claude Code?

Run this command in your terminal: claude mcp add slivingdoc --env SLIVINGDOC_TOKEN='<SLIVINGDOC_TOKEN>' -- npx -y slivingdoc

What are the best alternatives to slivingdoc?

The closest alternatives to slivingdoc are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to slivingdoc

  1. 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
  2. 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
  3. 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
  4. 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
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity