How does authentication work?
The server uses OAuth2 credentials from a Google Cloud project. It supports setting tokens directly in the `.env` file or storing them in a `.credentials.json` file, and automatically refreshes expired access tokens.
@overlay-one
Basic information
No overview available yet
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server for Google Tasks that enables AI assistants to interact with Google Tasks through the MCP protocol. It allows listing, creating, updating, deleting, and searching tasks and task lists, with OAuth2 authentication and automatic token refresh.
Clone the repository, install dependencies with pnpm install, and build with pnpm build. Set up a Google Cloud project, enable the Tasks API, create OAuth 2.0 credentials, and configure the .env file with CLIENT_ID, CLIENT_SECRET, and REDIRECT_URI. Start the server with pnpm start, then connect Claude Desktop using claude mcp --command "node /path/to/dist/index.js" or a configuration file.
The server uses OAuth2 credentials from a Google Cloud project. It supports setting tokens directly in the `.env` file or storing them in a `.credentials.json` file, and automatically refreshes expired access tokens.
You must create a project in the Google Cloud Console, enable the Tasks API, and create OAuth 2.0 credentials with a Web application type and a redirect URI (e.g., http://localhost:3000/oauth2callback).
Yes, the README provides detailed setup instructions for integrating with Claude Desktop, including command-line and configuration file approaches, along with example conversations and troubleshooting tips.
Check the server logs for specific error details. Ensure you are using compatible versions of Claude Desktop and the MCP SDK, and verify that the server is running before connecting.
It requires Node.js, pnpm, and a Google Cloud project with the Tasks API enabled. The server runs on standard input/output channels (stdio) for MCP communication.

Model Context Protocol Servers
🚀 The fast, Pythonic way to build MCP servers and clients.

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Health by Dr Brad works out a health plan from your own results: which screening is due at your age, and evidence-based suggestions, each with the reason and the published guideline or study behind it. Your record is one

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Comments