keep-mcp

keep-mcp

Connect Google Keep notes to the Model Context Protocol ecosystem.

View on GitHub
52
Stars
19
Forks
52
Watchers
3
Issues
Provides an MCP server interface for Google Keep, enabling standardized interaction with Keep notes via the Model Context Protocol. Allows users to search, create, update, and delete Google Keep notes through MCP, supporting integration with MCP-compatible platforms. It restricts modification and deletion operations to notes managed by the MCP server unless configured otherwise. Credentials for Google authentication are securely handled through environment variables.

Key Features

MCP server implementation for Google Keep
Find/search notes based on query strings
Create notes with custom title and text
Update note title and content
Delete notes (with restrictions for data safety)
Credential management with environment variables
UNSAFE_MODE to override note modification restrictions
Integration with external tools via MCP
Support for automated workflows
Guidance for secure publishing to PyPI

Use Cases

Integrate Google Keep notes into MCP-powered AI workflows
Automate note-taking based on MCP model interactions
Synchronize context notes between MCP tools and Google Keep
Programmatically create or update Google Keep notes from model outputs
Batch search and retrieve Google Keep notes for context-aware systems
Enable context persistence for assistants or bots using Google Keep
Enforce safe note modification policies in automated environments
Leverage Google authentication for secure third-party note management
Connect Google Keep to standardized context management systems
Enable fine-grained programmatic deletion of notes by context-aware applications

README

keep-mcp

MCP server for Google Keep

keep-mcp

How to use

  1. Add the MCP server to your MCP servers:
json
  "mcpServers": {
    "keep-mcp-pipx": {
      "command": "pipx",
      "args": [
        "run",
        "keep-mcp"
      ],
      "env": {
        "GOOGLE_EMAIL": "Your Google Email",
        "GOOGLE_MASTER_TOKEN": "Your Google Master Token - see README.md"
      }
    }
  }
  1. Add your credentials:
  • GOOGLE_EMAIL: Your Google account email address
  • GOOGLE_MASTER_TOKEN: Your Google account master token

Check https://gkeepapi.readthedocs.io/en/latest/#obtaining-a-master-token and https://github.com/simon-weber/gpsoauth?tab=readme-ov-file#alternative-flow for more information.

Features

  • find: Search for notes based on a query string
  • create_note: Create a new note with title and text (automatically adds keep-mcp label)
  • update_note: Update a note's title and text
  • delete_note: Mark a note for deletion

By default, all destructive and modification operations are restricted to notes that have were created by the MCP server (i.e. have the keep-mcp label). Set UNSAFE_MODE to true to bypass this restriction.

"env": {
  ...
  "UNSAFE_MODE": "true"
}

Publishing

To publish a new version to PyPI:

  1. Update the version in pyproject.toml
  2. Build the package:
    bash
    pipx run build
  3. Upload to PyPI:
    bash
    pipx run twine upload --repository pypi dist/*

Troubleshooting

Star History

Star History Chart

Repository Owner

feuerdev
feuerdev

User

Repository Details

Language Python
Default Branch main
Size 46 KB
Contributors 2
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

Python
100%

Tags

note-management context integration python-server automation

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • MCP Obsidian Server

    MCP Obsidian Server

    Integrate Obsidian note management with AI models via the Model Context Protocol.

    MCP Obsidian Server acts as a bridge between Obsidian and AI models by providing an MCP-compatible server interface. It enables programmatic access to Obsidian vaults through a local REST API, allowing operations like listing files, searching, reading, editing, and deleting notes. Designed to work with Claude Desktop and other MCP-enabled clients, it exposes a set of tools for efficient note and content management within Obsidian.

    • ⭐ 2,394
    • MCP
    • MarkusPfundstein/mcp-obsidian
  • MyMCP Server (All-in-One Model Context Protocol)

    MyMCP Server (All-in-One Model Context Protocol)

    Powerful and extensible Model Context Protocol server with developer and productivity integrations.

    MyMCP Server is a robust Model Context Protocol (MCP) server implementation that integrates with services like GitLab, Jira, Confluence, YouTube, Google Workspace, and more. It provides AI-powered search, contextual tool execution, and workflow automation for development and productivity tasks. The system supports extensive configuration and enables selective activation of grouped toolsets for various environments. Installation and deployment are streamlined, with both automated and manual setup options available.

    • ⭐ 93
    • MCP
    • nguyenvanduocit/all-in-one-model-context-protocol
  • mcp-kibela

    mcp-kibela

    MCP server for secure, AI-assisted access to Kibela notes.

    mcp-kibela is a Model Context Protocol (MCP) server implementation that enables AI assistants to search, retrieve, create, and update content from Kibela, a team knowledge-sharing platform. It provides standardized endpoints for note search, fetching individual or recent notes, and managing note content. Integrating with tools like Claude, Cursor, and VSCode, it allows seamless, secure access to organizational knowledge through MCP-enabled clients. Authentication via environment variables ensures secure connections to Kibela APIs.

    • ⭐ 12
    • MCP
    • kj455/mcp-kibela
  • anki-mcp

    anki-mcp

    MCP server for seamless integration with Anki via AnkiConnect.

    An MCP server that bridges Anki flashcards with the Model Context Protocol, exposing AnkiConnect functionalities as standardized MCP tools. It organizes Anki actions into intuitive services covering decks, notes, cards, and models for easy access and automation. Designed for integration with AI assistants and other MCP-compatible clients, it enables operations like creating, modifying, and organizing flashcards through a unified protocol.

    • ⭐ 6
    • MCP
    • ujisati/anki-mcp
  • Apple Notes MCP Server

    Apple Notes MCP Server

    Enables Claude Desktop to access and interact with local Apple Notes.

    Apple Notes MCP Server reads and provides access to local Apple Notes databases for use in Claude Desktop. It allows querying all notes, retrieving specific note content, and searching notes, facilitating deeper context integration for AI workflows. The server operates under the Model Context Protocol (MCP) and is designed for straightforward installation and integration. Currently, it supports reading and searching but does not handle encrypted notes, attachments, or note creation/editing.

    • ⭐ 121
    • MCP
    • sirmews/apple-notes-mcp
  • Make MCP Server (legacy)

    Make MCP Server (legacy)

    Enable AI assistants to utilize Make automation workflows as callable tools.

    Make MCP Server (legacy) provides a Model Context Protocol (MCP) server that connects AI assistants with Make scenarios configured for on-demand execution. It parses and exposes scenario parameters, allowing AI systems to invoke automation workflows and receive structured JSON outputs. The server supports secure integration through API keys and facilitates seamless communication between AI and Make's automation platform.

    • ⭐ 142
    • MCP
    • integromat/make-mcp-server
    • View all Alternatives

    Didn't find tool you were looking for?

    Be as detailed as possible for better results