@imenam/mcp-documentor

An MCP server to create, manage, and search project documentation — with staleness tracking and optional semantic search.

Connect it to Cursor, Claude Desktop, or any MCP-compatible agent to let your AI document, browse and verify your codebase docs without leaving the chat.

Features

• Create & update docs — write markdown documentation entries linked to source files; prefer partial edits via patch_doc
• Staleness tracking — automatically detects when tracked files have changed since the last doc update
• Semantic search — find relevant docs by meaning (requires an OpenAI API key)
• Multi-project support — organize docs into separate projects; MCP tools work across projects; set_project only changes what the GUI shows
• GUI — built-in web interface when a proxy is configured (PROXY_URL); without it, the GUI worker is not started
• Proxy-aware — integrates with the proxy-setup for GUI exposure
• Links & structure — check_links, get_doc_tree, move_doc, and git_diff_doc for maintenance workflows

Installation

npx -y @imenam/mcp-documentor

Or install globally:

npm install -g @imenam/mcp-documentor

Global install exposes:

• mcp-documentor — MCP server
• mcp-documentor-migrate — CLI helper for migrating inline doc links (see scripts/migrate-links.js)

MCP Configuration

Add to your MCP client config (e.g. Cursor mcp.json):

{
  "mcpServers": {
    "mcp-documentor": {
      "command": "npx",
      "args": ["-y", "@imenam/mcp-documentor"],
      "env": {
        "OPENAI_API_KEY": "sk-..."
      }
    }
  }
}

Environment Variables

| Variable | Required | Description | |---|---|---| | OPENAI_API_KEY | No | Enables semantic search via OpenAI embeddings (search_docs) | | MCP_DOCUMENTOR_OPENAI_MODEL | No | Embedding model (default: text-embedding-3-small) | | PROXY_URL | No | URL of the proxy server to register and launch the GUI | | MCP_DATA_DIR | No | Overrides the default data directory (see Data storage) |

Optional .env at the package root (directory containing package.json discovered from the installed binary) is loaded when present.

Available Tools

| Tool | Description | |---|---| | create_doc | Create a new documentation entry linked to source files | | get_doc | Retrieve a documentation entry with full content | | get_doc_metadata | Get metadata and freshness status without loading content | | list_docs | List docs with staleness indicators (optionally filter by project) | | get_doc_tree | Return folder/doc structure for a project (or all projects) | | update_doc | Fully replace content and/or metadata (prefer patch_doc for small edits) | | patch_doc | Search-and-replace a fragment of a doc’s content | | move_doc | Change a doc’s path (folder/name); use after renames to fix links | | delete_doc | Permanently delete a documentation entry | | search_docs | Semantic search over docs (natural language; requires OpenAI) | | check_freshness | Staleness for one doc or a full project scan | | refresh_file_snapshot | Mark tracked files as up-to-date without editing the doc | | git_diff_doc | Git diff for tracked files vs snapshot baseline | | check_links | Validate related_docs, doc:// links, and #heading anchors | | list_projects | List all documentation projects | | set_project | Switch the active project for the GUI only (not for MCP tools) |

Data Storage

By default, data lives under .docs-data next to the resolved package root (the folder that contains package.json for the running install). Set MCP_DATA_DIR to use another directory. Contents include projects, SQLite/embeddings, and logs under .docs-data/logs. This tree is not part of the npm package; it is created at runtime.

License

ISC