Skip to main content

MCP server that wraps the Open Notebook API

Project description

Open Notebook MCP Server

An MCP (Model Context Protocol) server that provides tools to interact with the Open Notebook API. This server enables AI assistants like Claude to manage notebooks, sources, notes, search content, and interact with AI models through Open Notebook.

Features

  • Notebooks Management: Create, read, update, and delete notebooks
  • Sources Management: Add and manage content sources (links, uploads, text)
  • Notes Management: Create and organize notes within notebooks
  • Search & AI: Search content using vector/text search and ask questions
  • Models Management: Configure and manage AI models
  • Chat Sessions: Create and manage chat conversations
  • Settings: Access and update application settings
  • Progressive Disclosure: Efficient tool discovery with search_capabilities

Installation

Using uv (recommended)

# Clone the repository
git clone https://github.com/PiotrAleksander/open-notebook-mcp.git
cd open-notebook-mcp

# Install with uv
uv sync

Using pip

pip install -e .

Configuration

The server requires configuration to connect to your Open Notebook instance:

Environment Variables

Create a .env file or set these environment variables:

# Required: URL of your Open Notebook instance
OPEN_NOTEBOOK_URL=http://localhost:5055

# Optional: Authentication password (if APP_PASSWORD is set in Open Notebook)
OPEN_NOTEBOOK_PASSWORD=your_password_here

# Optional: Transport configuration (default: stdio)
MCP_TRANSPORT=stdio  # or streamable-http for remote deployment

Example Configuration

For local development with default Open Notebook settings:

# .env
OPEN_NOTEBOOK_URL=http://localhost:5055

If you've configured authentication in Open Notebook:

# .env
OPEN_NOTEBOOK_URL=http://localhost:5055
OPEN_NOTEBOOK_PASSWORD=my_secure_password

Usage

Running the Server

Development Mode (STDIO)

For local use with AI assistants:

uv run open-notebook-mcp

Or using the MCP CLI:

mcp dev src/open_notebook_mcp/server.py

Production Mode (Streamable HTTP)

For remote deployment:

MCP_TRANSPORT=streamable-http HOST=0.0.0.0 PORT=8000 uv run open-notebook-mcp

Using with Claude Desktop

Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "open-notebook": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/open-notebook-mcp",
        "open-notebook-mcp"
      ],
      "env": {
        "OPEN_NOTEBOOK_URL": "http://localhost:5055",
        "OPEN_NOTEBOOK_PASSWORD": "your_password_if_needed"
      }
    }
  }
}

Discovering Available Tools

The server implements progressive disclosure. Use the search_capabilities tool to discover available functionality:

# Get a summary of all tools
search_capabilities(query="", detail="summary", limit=50)

# Search for specific functionality
search_capabilities(query="notebook", detail="summary", limit=10)

# Get full details for a specific tool
search_capabilities(query="create_notebook", detail="full", limit=1)

Example Workflows

Creating and Managing Notebooks

# Create a new notebook
result = create_notebook(
    name="AI Research",
    description="Research on AI applications"
)
notebook_id = result["notebook"]["id"]

# List all notebooks
notebooks = list_notebooks(archived=False, limit=20)

# Update a notebook
update_notebook(
    notebook_id=notebook_id,
    name="AI Research (Updated)"
)

# Get a specific notebook
notebook = get_notebook(notebook_id=notebook_id)

Adding Sources

# Add a web source
source = create_source(
    notebook_id=notebook_id,
    type="link",
    url="https://example.com/ai-article",
    title="AI Research Article",
    embed=True  # Generate embeddings
)

# List sources in a notebook
sources = list_sources(notebook_id=notebook_id, limit=20)

Creating Notes

# Create a note
note = create_note(
    notebook_id=notebook_id,
    title="Key Findings",
    content="Important insights about AI applications...",
    topics=["AI", "Research"]
)

# Update a note
update_note(
    note_id=note["note"]["id"],
    content="Updated insights..."
)

Searching and Asking Questions

# Search content
results = search(
    query="artificial intelligence",
    type="vector",
    notebook_id=notebook_id,
    limit=10
)

# List available models first
models = list_models(limit=50)
model_id = models["models"][0]["id"]

# Ask a question
answer = ask_simple(
    question="What are the main AI applications mentioned?",
    strategy_model=model_id,
    answer_model=model_id,
    final_answer_model=model_id,
    notebook_id=notebook_id
)

Chat Sessions

# Create a chat session
session = create_chat_session(
    notebook_id=notebook_id,
    title="Research Discussion"
)
session_id = session["session"]["id"]

# Build context
context = get_chat_context(notebook_id=notebook_id)

# Send a message
response = execute_chat(
    session_id=session_id,
    message="What are the key insights from my research?",
    context=context["context"]
)

# Get session history
history = get_chat_session(session_id=session_id)

Available Tools

The server provides 39 tools across multiple categories:

Meta Tools

  • search_capabilities - Progressive tool discovery

Notebooks (5 tools)

  • list_notebooks, get_notebook, create_notebook, update_notebook, delete_notebook

Sources (5 tools)

  • list_sources, get_source, create_source, update_source, delete_source

Notes (5 tools)

  • list_notes, get_note, create_note, update_note, delete_note

Search (3 tools)

  • search, ask_question, ask_simple

Models (5 tools)

  • list_models, get_model, create_model, delete_model, get_default_models

Chat (7 tools)

  • list_chat_sessions, create_chat_session, get_chat_session, update_chat_session, delete_chat_session, execute_chat, get_chat_context

Settings (2 tools)

  • get_settings, update_settings

Architecture

This server follows MCP best practices:

  • Progressive Disclosure: Use search_capabilities to minimize context usage
  • Context Efficiency: Small outputs by default, with limit parameters
  • Dual Transport: Supports both STDIO (local) and Streamable HTTP (remote)
  • Error Handling: Structured error messages with actionable hints
  • Timeouts: 30-second default timeout for all API requests
  • Authentication: Optional Bearer token authentication

Development

Project Structure

open-notebook-mcp/
├── src/
│   └── open_notebook_mcp/
│       ├── __init__.py
│       └── server.py          # Main MCP server implementation
├── tests/                      # (to be added)
├── pyproject.toml
├── README.md
└── .env.example

Testing

Test the server using the MCP Inspector:

mcp dev src/open_notebook_mcp/server.py

or

npx @modelcontextprotocol/inspector uv --directory ./src/open_notebook_mcp "run" "server.py"

This opens an interactive inspector where you can:

  1. Browse available tools
  2. Test tool calls
  3. Inspect responses
  4. Debug errors

Adding New Tools

To add new tools:

  1. Add a Capability entry to the CAPABILITIES tuple
  2. Implement the tool function with @mcp.tool() decorator
  3. Follow naming conventions: verb_noun (e.g., list_notebooks)
  4. Include proper docstrings and type hints
  5. Return structured responses with request_id

Requirements

  • Python 3.12+
  • Open Notebook instance (local or remote)
  • Dependencies: mcp[cli]>=1.23.2, httpx>=0.28.1

Contributing

Contributions are welcome! Please ensure:

  • Follow the existing code structure and patterns
  • Add tools to the CAPABILITIES index
  • Include proper type hints and docstrings
  • Test with MCP Inspector before submitting

License

See LICENSE file for details.

Links

Support

For issues related to:

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

open_notebook_mcp-0.3.0.tar.gz (10.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

open_notebook_mcp-0.3.0-py3-none-any.whl (11.7 kB view details)

Uploaded Python 3

File details

Details for the file open_notebook_mcp-0.3.0.tar.gz.

File metadata

  • Download URL: open_notebook_mcp-0.3.0.tar.gz
  • Upload date:
  • Size: 10.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for open_notebook_mcp-0.3.0.tar.gz
Algorithm Hash digest
SHA256 4525535a8c62c78c77004636ad018e7b1bf7a8eadc3f703d9e915003f36e8127
MD5 0b981cea68d90eb5944db535cefee36c
BLAKE2b-256 540cdb620ddcea40667fdea1b1d07a6f3e24ca4a198ab9f770d1cc3d68c942c7

See more details on using hashes here.

File details

Details for the file open_notebook_mcp-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: open_notebook_mcp-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 11.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for open_notebook_mcp-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3ee108092cb7fd0e1ee5e10aeec35bb7d0eb4fe9319d2af13270aab2c9cb744e
MD5 862e900fe1f0917c60733a0dc59a305b
BLAKE2b-256 aa5bfde76e11ec787490c4cc7a1a553a1cb5a67f87a3f0e059079c18a9fa4157

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page