File AI

io.github.flyfish-devPublished by GitHub account flyfish-devv0.1.1Updated Oct 24, 2026

Agent-ready local document context with stable anchors.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Read-only MCP server that turns local documents into structured profiles, anchors, chunks, outlines, and searchable context for agents.

What you can do
File AI parses local files and caches a document index, then exposes tools to read blocks, chunks, or anchors, search cached content with source anchors, and retrieve nearby context around an anchor or query. It also lists supported formats and renderer capabilities. Every content block carries an anchor such as a page, slide, worksheet, row range, or byte location, so agents can cite document-grounded claims.
When to use it
Use it when an assistant needs to understand local documents such as PDF, DOCX, XLSX/CSV, PPTX, EML, Markdown, JSON, or archives without reverse-engineering their internal formats. It suits document-grounded question answering, summarization, and retrieval where stable citations matter.
Requirements
Runs locally as a stdio process, typically via npx @flyfish-dev/file-ai or a global npm install. Node.js and npm are required. No authentication, environment variables, or headers are declared. It can also run over streamable HTTP on a local host and port.
Before you install
The server is described as read-only and does not mutate source documents. It reads local files, so it can expose document content to the connected assistant; consider which files and directories you point it at. Formats without a structured text extractor return best-effort metadata and explicit warnings.

Installation

In SourceWeft

  1. Open File AI in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

File AI

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.

MCP Registry name: io.github.flyfish-dev/file-ai

Install

Use it directly with npx:

bash
npx -y @flyfish-dev/file-ai

Or install it globally:

bash
npm install -g @flyfish-dev/file-aifile-ai --transport stdio

MCP Client Config

Stdio:

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

Streamable HTTP:

bash
npx -y @flyfish-dev/file-ai --transport http --host 127.0.0.1 --port 8765

Endpoint:

text
http://127.0.0.1:8765/mcp

Tools

  • 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.

Resources

  • doc://{indexId}/profile
  • doc://{indexId}/outline
  • doc://{indexId}/chunks

Supported Files

File AI recognizes formats through @file-viewer/core/headless, currently covering 206 registered extensions. profile.format is therefore aligned with the same renderer selection used by Flyfish File Viewer.

Content extraction is a separate layer. File AI provides structured awareness for text/code/Markdown/JSON, PDF text, DOCX, XLSX/CSV, PPTX, EML, and archive manifests. Other File Viewer renderer-only formats such as CAD, 3D, media, image, geospatial, drawing, ebook, and data assets are still recognized in profile.format; when no structured text extractor exists yet, File AI returns a profile plus best-effort metadata/text and explicit warnings in profile.warnings and profile.extraction.

Every content block carries an anchor such as a page, slide, worksheet, row range, nested path, or byte/text location. Agents should cite returned anchorId values when making document-grounded claims.

Development

bash
pnpm installpnpm buildpnpm testpnpm validate:skill

Run locally:

bash
pnpm dev -- --transport stdiopnpm dev -- --transport http --port 8765

Publishing

The package includes:

  • npm metadata for @flyfish-dev/file-ai
  • MCP Registry metadata in server.json
  • GitHub Actions workflow .github/workflows/publish-mcp.yml

Release flow:

bash
git tag v0.1.0git push origin v0.1.0

The workflow publishes the npm package first, then publishes io.github.flyfish-dev/file-ai to the official MCP Registry through GitHub OIDC. The repository must have an NPM_TOKEN secret that can publish @flyfish-dev/file-ai.

The server is read-only. It does not mutate source documents.

Source: README.md at commit b4a1869

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts