Skip to content
MCP server

MCP Databnf

Search the BnF open catalogue for authors, works, editions and digitised copies

Runs locallyStatus and history
Pricing
Free
Platforms
CLI
Runs
Locally
Version
2.2.0
Listing updated
2 days ago

About MCP Databnf

MCP Databnf is a free MCP server for books and literature. It runs locally on your machine and is started by your AI client.

The Bibliothèque nationale de France publishes authority records for the people it catalogues, with dates, places, languages and fields of activity; the works they wrote; the editions of each work; and links to copies digitised in Gallica. This server connects a chat client to data.bnf.fr and needs no key or account. Records state whether the library considers them established or still provisional, and get_work spells out what that means.

The usual path runs from a search to a record: a search row carries an id that get_author or get_work reads. Search results include words_searched, has_more and index_window_full so you can tell what was actually sent and whether more pages exist. Missing fields come back as null rather than guessed.

It is polite to the service: the minimum interval between requests defaults to 3,000 ms, which is also the floor, answers are cached for 15 minutes by default, and you can set a user agent that identifies your client. It needs Node 24 or later, and installs from npm, Docker or an .mcpb bundle.

Install

Run in a terminal

claude mcp add mcp-databnf -- npx -y mcp-databnf

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-databnf": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-databnf"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-databnf": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-databnf"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-databnf": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-databnf"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "mcp-databnf": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-databnf"
      ]
    }
  }
}

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

{
  "mcpServers": {
    "mcp-databnf": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-databnf"
      ]
    }
  }
}

Configuration

  • BNF_USER_AGENTIdentify your own client. The project's own identifier is appended, so the BnF can always reach a person.
  • BNF_MIN_INTERVAL_MSMinimum milliseconds between requests. Default 3000, which is also the floor.
  • BNF_TIMEOUT_MSDeadline for one SPARQL query, in milliseconds. Default 60000.
  • BNF_MAX_RETRIESAttempts after a busy answer. Default 3.
  • BNF_CACHE_TTL_MSHow long an answer is kept in memory, in milliseconds. Default 900000. Zero turns the cache off.
  • BNF_LOG_LEVELsilent, error, info or debug. Default error. Logs go to stderr.

Tools this server provides (7)

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

search_authors
Finds people by name in the authority records
get_author
Reads one person's record in full
search_works
Finds works by title
get_work
Reads one work's record in full
list_works
Lists the works one person is credited with
list_editions
Lists the editions of one work
find_digitised
Finds Gallica copies for a person or a work

What it does

Author search
`search_authors` finds people by name in the authority records.
Work search
`search_works` finds works by title with established or provisional status.
Full records
`get_author` and `get_work` return dates, places, languages, subjects and Dewey classes.
Editions list
`list_editions` shows the editions of a work.
Gallica links
`find_digitised` finds digitised copies for a person or work.
Polite rate limiting
3-second minimum between requests, with caching and retries.

Good for

  • Look up an author's dates, places and languages
  • List everything a writer is credited with
  • Find which editions of a work the BnF holds
  • Find a digitised copy in Gallica
  • Check whether a record is established or provisional

Pricing

Free

No API key or account needed

MCP Databnf FAQ

Does it need an API key?

No key or account is needed.

What data source does it use?

data.bnf.fr, the open data service of the Bibliothèque nationale de France.

Why is it slow?

It waits at least 3,000 ms between requests, which is the floor, out of consideration for the service.

What Node version is required?

Node 24 or later.

How do I install it?

`claude mcp add databnf -- npx -y mcp-databnf`, Docker, or the `.mcpb` bundle.

Is MCP Databnf free?

Yes. MCP Databnf is free to use.

How do I add MCP Databnf to Claude Code?

Run this command in your terminal: claude mcp add mcp-databnf -- npx -y mcp-databnf

What are the best alternatives to MCP Databnf?

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

Alternatives to MCP Databnf

  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