A Model Context Protocol (MCP) server for document ingestion, chunking, semantic search, and note management.
Connect Doc Lib MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A Model Context Protocol (MCP) server for document ingestion, chunking, semantic search, and note management. The doc lib mcp mcp server is what makes that connection.
The server ships on npm as @modelcontextprotocol/inspector, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
add-note — Add a new note to the in-memory note storeArguments — name (string), content (string)ingest-string — Ingest and chunk a markdown or plain text string provided via messageingest-markdown — Ingest and chunk a markdown (.md) fileingest-python — Ingest and chunk a Python (.py) fileingest-openapi — Ingest and chunk an OpenAPI JSON fileingest-html — Ingest and chunk an HTML fileingest-html-url — Ingest and chunk HTML content from a URL (optionally using Playwright for dynamic content)smart_ingestion — Extracts all technically relevant content from a file using Gemini, then chunks it using robust markdown logicsearch-chunks — Semantic search over ingested contentdelete-source — Delete all chunks from a given sourcedelete-chunk-by-id — Delete one or more chunks by idConfiguration is passed through the environment: OLLAMA_HOST, RERANKER_MODEL_PATH, UV_PUBLISH_TOKEN. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Doc Lib MCP's toolset — add-note, Arguments, ingest-string and 11 more — is a fair guide to whether it matches your workflow. It is maintained by shifusen329; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| add-note | Add a new note to the in-memory note store |
| Arguments | name (string), content (string) |
| ingest-string | Ingest and chunk a markdown or plain text string provided via message |
| ingest-markdown | Ingest and chunk a markdown (.md) file |
| ingest-python | Ingest and chunk a Python (.py) file |
| ingest-openapi | Ingest and chunk an OpenAPI JSON file |
| ingest-html | Ingest and chunk an HTML file |
| ingest-html-url | Ingest and chunk HTML content from a URL (optionally using Playwright for dynamic content) |
| smart_ingestion | Extracts all technically relevant content from a file using Gemini, then chunks it using robust markdown logic. |
| search-chunks | Semantic search over ingested content |
| delete-source | Delete all chunks from a given source |
| delete-chunk-by-id | Delete one or more chunks by id |
| update-chunk-type | Update the type attribute for a chunk by id |
| ingest-batch | Ingest and chunk multiple documentation files (markdown, OpenAPI JSON, Python) in batch |
"mcpServers": {
"doc-lib-mcp": {
"command": "uv",
"args": [
"--directory",
"/home/administrator/python-share/doc-lib-mcp",
"run",
"doc-lib-mcp"
]
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| OLLAMA_HOST | Endpoint or connection string the server talks to. | Optional |
| RERANKER_MODEL_PATH | Filesystem location the server is allowed to use. | Optional |
| UV_PUBLISH_TOKEN | Credential the server authenticates with. | Yes |
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.