An MCP server that connects to the Open Notebook API so AI assistants can manage notebooks, sources, notes, models, chat sessions, settings, and search content. It supports local stdio and remote HTTP transport, with progressive tool discovery via `search_capabilities`.
From the registry: MCP server that wraps the Open Notebook API
$ git clone https://github.com/PiotrAleksander/open-notebook-mcp.git && cd open-notebook-mcp && uv syncPlease install the `open-notebook` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone and install** — Clone the repo and run `uv sync`. Run: `git clone https://github.com/PiotrAleksander/open-notebook-mcp.git && cd open-notebook-mcp && uv sync`
- **Open Notebook instance** — Requires a running Open Notebook instance (local or remote). (https://github.com/lfnovo/open-notebook)
Canonical MCP server config (stdio transport):
- command: `uv`
- args: ["run","--directory","/path/to/open-notebook-mcp","open-notebook-mcp"]
- required environment variables:
- `OPEN_NOTEBOOK_URL`: URL of your Open Notebook instance. (example: `http://localhost:5055`)
- optional environment variables:
- `OPEN_NOTEBOOK_PASSWORD`: Password if APP_PASSWORD is set in Open Notebook. (example: `<your-password>`)
- `MCP_TRANSPORT`: Transport: stdio or streamable-http. (example: `stdio`)
Note: Not published to PyPI. 39 tools for Open Notebook API integration.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPEN_NOTEBOOK_URLrequiredURL of the Open Notebook instance to connect to.Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…