Skip to main content
Glama
homeserverhq

OpenNotebook MCP Proxy Server

by homeserverhq

OpenNotebook MCP Multitenant Proxy Server

This repository contains a Model Context Protocol (MCP) server that acts as a secure, multi-tenant proxy between an AI Assistant and the OpenNotebook backend API. It exposes 81 MCP tools covering 14 resource domains with full CRUD, search, chat, podcast, and command management.

โœจ Features

  • ๐Ÿ”‘ Identity Passthrough โ€” Extracts the Authorization: Bearer <token> header from incoming HTTP requests and forwards it to the OpenNotebook API without server-side authentication.

  • ๐Ÿ‘ฅ Multi-Tenancy โ€” Uses Python contextvars to maintain thread-safe user identity isolation, ensuring all AI-driven actions are scoped to the authenticated user's permissions.

  • ๐Ÿ“Š Full OpenNotebook Coverage โ€” 81 tools mapped to OpenNotebook API endpoints across 14 resource domains.

  • โšก TOON Optimization โ€” Bulk list responses are automatically compressed using TOON (Token-Optimized Object Notation) to reduce token consumption and maximize context window efficiency.

  • ๐Ÿš€ Efficient Gets โ€” GET responses return only commonly used fields by default. Full objects are available via an include_all_fields flag.

  • ๐Ÿงช Comprehensive Testing โ€” 109 automated tests covering all tool domains, run via the test runner pipeline.

  • ๐Ÿท๏ธ Tool Annotations โ€” All tools expose standard MCP ToolAnnotations hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint). The tags field carries grouping metadata (basic/primary/advanced + opennotebook).

Related MCP server: NotebookLM MCP Server

๐Ÿ”ง Environment Variables

Variable

Required

Description

OPENNOTEBOOK_BASE_URL

Yes

Docker-internal URL of the OpenNotebook API

MCP_SERVER_PORT

Yes

Port number the MCP server listens on

ALLOW_ALL_AGGREGATE

No

When true, aggregate listing tools honor the include_all_fields parameter. When false (default), the parameter is silently forced to False for aggregate list operations.

IS_STATEFUL

No

When true, uses stateful Streamable HTTP with session tracking. When false (default), uses stateless mode.

๐Ÿ“ฆ Installation & Local Development

  1. Ensure you have Python 3.12+ installed.

  2. Install dependencies:

    pip install fastmcp httpx pydantic uvicorn toon-mcp-server
  3. Run the server:

    export OPENNOTEBOOK_BASE_URL=http://localhost:5055
    export MCP_SERVER_PORT=80
    python -m src.main

๐Ÿณ Docker Deployment

Build and run the server using Docker:

docker build -t opennotebook-mcp:latest .
docker run -d --name opennotebook-mcp \
    -e OPENNOTEBOOK_BASE_URL="http://opennotebook-app:5055" \
    -e MCP_SERVER_PORT=80 \
    opennotebook-mcp:latest

The MCP server serves at http://opennotebook-mcp:80/mcp (Streamable HTTP).

โš ๏ธ Important Notes

  • ๐Ÿ“‹ include_all_fields โ€” The include_all_fields parameter (available on all get_* and list_* tools) controls whether all available fields are included in responses. Defaults to False for performance; set to True only when additional fields are needed.

  • โšก TOON Compression โ€” All bulk list responses are automatically compressed using TOON to reduce token consumption by 30โ€“60%.

  • ๐Ÿ“ Required Fields & Defaults โ€” Each create_* tool requires specific key fields. All other fields default to empty strings or reasonable values. The owner field is automatically set to the authenticated user for most resources.

๐Ÿ› ๏ธ API Tool Mapping

The server implements 81 MCP tools organized into the following categories:

๐Ÿ““ Notebooks (9 tools)

  • check_server_status โ€” Check the health and status of the OpenNotebook backend API

  • list_all_notebooks โ€” List all notebook records

  • get_notebook_by_id โ€” Get a single notebook by ID

  • create_notebook โ€” Create a new notebook

  • update_notebook โ€” Update an existing notebook

  • delete_notebook_by_id โ€” Delete a notebook by ID

  • get_notebook_delete_preview โ€” Get a preview of what will be deleted

  • add_source_to_notebook โ€” Add an existing source to a notebook

  • remove_source_from_notebook โ€” Remove a source from a notebook

  • list_recently_viewed โ€” List recently viewed items

๐Ÿ“ Notes (5 tools)

  • list_all_notes โ€” List all note records

  • get_note_by_id โ€” Get a single note by ID

  • create_note โ€” Create a new note

  • update_note โ€” Update an existing note

  • delete_note_by_id โ€” Delete a note by ID

๐Ÿ”— Sources (8 tools)

  • list_all_sources โ€” List all source records

  • get_source_by_id โ€” Get a single source by ID

  • create_source โ€” Create a new source (link or text type)

  • update_source โ€” Update an existing source

  • delete_source_by_id โ€” Delete a source by ID

  • get_source_status โ€” Get processing status for a source

  • retry_source_processing โ€” Retry processing for a failed source

  • list_source_insights โ€” List all insights for a source

  • create_source_insight โ€” Start insight generation for a source

๐Ÿ’ก Insights (4 tools)

  • get_insight_by_id โ€” Get a single insight by ID

  • delete_insight_by_id โ€” Delete an insight by ID

  • save_insight_as_note โ€” Convert an insight to a note

  • list_source_insights โ€” List insights for a source

๐Ÿ” Search & Settings (4 tools)

  • search_knowledge_base โ€” Search the knowledge base

  • ask_knowledge_base_simple โ€” Ask the knowledge base a question

  • get_settings โ€” Get all application settings

  • update_settings โ€” Update application settings

๐Ÿค– Models (5 tools)

  • list_all_models โ€” List all configured models

  • create_model โ€” Create a new model configuration

  • delete_model_by_id โ€” Delete a model by ID

  • get_default_models โ€” Get default model assignments

  • update_default_models โ€” Update default model assignments

๐Ÿ”„ Transformations (8 tools)

  • list_all_transformations โ€” List all transformation records

  • get_transformation_by_id โ€” Get a single transformation by ID

  • create_transformation โ€” Create a new transformation

  • update_transformation โ€” Update an existing transformation

  • delete_transformation_by_id โ€” Delete a transformation by ID

  • execute_transformation โ€” Execute a transformation on input text

  • get_default_transformation_prompt โ€” Get the default prompt

  • update_default_transformation_prompt โ€” Update the default prompt

๐Ÿงฉ Embedding (3 tools)

  • embed_content โ€” Embed content for vector search

  • start_embedding_rebuild โ€” Start a background rebuild job

  • get_rebuild_status โ€” Get rebuild operation status

๐Ÿ’ฌ Chat (7 tools)

  • list_chat_sessions โ€” List chat sessions for a notebook

  • create_chat_session โ€” Create a new chat session

  • get_chat_session โ€” Get a chat session with messages

  • update_chat_session โ€” Update a chat session

  • delete_chat_session โ€” Delete a chat session

  • execute_chat โ€” Execute a chat request

  • build_chat_context โ€” Build notebook context

๐Ÿ”Œ Source Chat (5 tools)

  • create_source_chat_session โ€” Create a source chat session

  • list_source_chat_sessions โ€” List source chat sessions

  • get_source_chat_session โ€” Get a source chat session

  • update_source_chat_session โ€” Update a source chat session

  • delete_source_chat_session โ€” Delete a source chat session

๐ŸŽ™๏ธ Podcasts (6 tools)

  • generate_podcast โ€” Generate a podcast episode

  • get_podcast_job_status โ€” Get podcast job status

  • list_podcast_episodes โ€” List all podcast episodes

  • get_podcast_episode โ€” Get a specific episode

  • retry_podcast_episode โ€” Retry a failed episode

  • delete_podcast_episode โ€” Delete a podcast episode

๐ŸŽฌ Episode Profiles (6 tools)

  • list_episode_profiles โ€” List all episode profiles

  • get_episode_profile โ€” Get a profile by name

  • create_episode_profile โ€” Create a new episode profile

  • update_episode_profile โ€” Update an episode profile

  • delete_episode_profile โ€” Delete an episode profile

  • duplicate_episode_profile โ€” Duplicate an episode profile

๐Ÿ—ฃ๏ธ Speaker Profiles (6 tools)

  • list_speaker_profiles โ€” List all speaker profiles

  • get_speaker_profile โ€” Get a profile by name

  • create_speaker_profile โ€” Create a new speaker profile

  • update_speaker_profile โ€” Update a speaker profile

  • delete_speaker_profile โ€” Delete a speaker profile

  • duplicate_speaker_profile โ€” Duplicate a speaker profile

๐Ÿ“‹ Commands (4 tools)

  • submit_command_job โ€” Submit a command for background processing

  • get_command_job_status โ€” Get command job status

  • list_command_jobs โ€” List command jobs

  • cancel_command_job โ€” Cancel a running command job

A
license - permissive license
-
quality - not tested
B
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
โ€“Release cycle
โ€“Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Markdown-first MCP server for Notion API with 8 composite tools and 39 actions.

  • AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.

  • User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.

View all MCP Connectors

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/homeserverhq/opennotebook-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server