File AI MCP Server

Agent-ready local document context with stable anchors.

Local serverstdio

What is the File AI MCP server?

File AI MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Agent-ready local document context with stable anchors.

What you get

Read-only document awareness MCP server for agents. File AI uses Flyfish File Viewer core as the source of truth for format recognition, then turns local files into a stable profile, anchors, blocks, chunks, outline, search results, and contextual snippets so an agent can understand document content without reverse-engineering PDF, OOXML, spreadsheet, email, or archive internals.

What the assistant can call

Once File AI is connected, these are the calls the assistant has available:

  • doc_analyze — parse a local file and cache a document index
  • doc_read — read blocks, chunks, or anchors from an existing index or path
  • doc_search — search cached content with source anchors
  • doc_context — retrieve nearby blocks around an anchor or query
  • doc_list_formats — list File Viewer core registry formats, all supported extensions, renderer capabilities, and File AI extractor coverage

Setting it up

@flyfish-dev/file-ai on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. File AI's toolset — doc_analyze, doc_read, doc_search and 2 more — is a fair guide to whether it matches your workflow. It is maintained by flyfish-dev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the file ai mcp server does with a few real requests.

Available tools

ToolWhat it does
doc_analyzeparse a local file and cache a document index.
doc_readread blocks, chunks, or anchors from an existing index or path.
doc_searchsearch cached content with source anchors.
doc_contextretrieve nearby blocks around an anchor or query.
doc_list_formatslist File Viewer core registry formats, all supported extensions, renderer capabilities, and File AI extractor coverage.

How to install the File AI MCP server

{
  "mcpServers": {
    "file-ai": {
      "command": "npx",
      "args": ["-y", "@flyfish-dev/file-ai"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use File AI to doc analyze.
  • Use File AI to doc read.
  • Use File AI to doc search.

Frequently asked questions

It connects File AI to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (doc_analyze, doc_read, doc_search, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with File AI directly.