File AI
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@File AIAnalyze the quarterly report.docx and show its outline"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
File AI
Read-only document awareness MCP server for agents. File AI 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:
npx -y @flyfish-dev/file-aiOr install it globally:
npm install -g @flyfish-dev/file-ai
file-ai --transport stdioRelated MCP server: Docalyze
MCP Client Config
Stdio:
{
"mcpServers": {
"file-ai": {
"command": "npx",
"args": ["-y", "@flyfish-dev/file-ai"]
}
}
}Streamable HTTP:
npx -y @flyfish-dev/file-ai --transport http --host 127.0.0.1 --port 8765Endpoint:
http://127.0.0.1:8765/mcpTools
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 known Flyfish File Viewer formats.
Resources
doc://{indexId}/profiledoc://{indexId}/outlinedoc://{indexId}/chunks
Supported Files
File AI prioritizes text, Markdown, JSON, source code, PDF, DOCX, XLSX, CSV, PPTX, EML, and archive manifests. Unsupported or weakly structured files return a best-effort profile, extracted text when available, and warnings.
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
pnpm install
pnpm build
pnpm test
pnpm validate:skillRun locally:
pnpm dev -- --transport stdio
pnpm dev -- --transport http --port 8765Publishing
The package includes:
npm metadata for
@flyfish-dev/file-aiMCP Registry metadata in
server.jsonGitHub Actions workflow
.github/workflows/publish-mcp.yml
Release flow:
git tag v0.1.0
git push origin v0.1.0The 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.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/flyfish-dev/file-ai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server