Mist
MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.
What is Mist?
Mist is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server empowering ai assistants with real-world capabilities: gmail, calendar, tasks, git integration, and note management. bridges ai assistants to external services through standardized protocol...
MCP server empowering AI assistants with real-world capabilities: Gmail, Calendar, Tasks, Git integration, and note management. Bridges AI assistants to external services through standardized protocol with secure authentication.
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server empowering AI assistants with real-world capabili
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mistConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Mist
MIST (Model Intelligence System for Tasks) is a Python-based MCP server that bridges AI assistants to your Gmail, Google Calendar, Google Tasks, Git repositories, and local note storage through the Model Context Protocol. It handles OAuth2 authentication with Google services automatically on first run and exposes a unified set of tools so you can search emails, manage calendar events, track tasks, commit code, and maintain project notes — all from within your AI assistant.
Prerequisites
- Python 3.13 or newer
- UV package manager (recommended) or pip
- Google account with OAuth2 credentials (credentials.json from Google Cloud Console)
- Git installed for Git integration features
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the MIST repository to your local machine and navigate into the project directory.
git clone https://github.com/CLoaKY233/MIST.git
cd MISTInstall dependencies
Install project dependencies using UV (recommended) or pip. UV manages a virtual environment automatically.
uv install
# Or with pip:
pip install -e .Obtain Google OAuth credentials
Go to the Google Cloud Console, create a project, enable the Gmail, Calendar, and Tasks APIs, then download credentials.json for an OAuth 2.0 Desktop client. Place the file in a known path on your system.
Create the .env configuration file
Create a .env file in the MIST project root with the three required environment variables pointing to your notes directory and Google credential files.
MIST_NOTES_DIR=/path/to/your/notes
MIST_GOOGLE_CREDENTIALS_PATH=/path/to/credentials.json
MIST_GOOGLE_TOKEN_PATH=/path/to/token.jsonConfigure your MCP client
Add MIST to your Claude Desktop configuration. Replace /path/to/mist with the actual absolute path where you cloned the repository.
{
"mcpServers": {
"M.I.S.T.": {
"command": "uv",
"args": [
"run",
"--with", "mcp[cli]",
"--with-editable", "/path/to/mist",
"mcp", "run", "/path/to/mist/mist/server.py"
]
}
}
}Authenticate with Google on first run
Start Claude Desktop or restart it after saving the config. On the first tool call that touches Gmail/Calendar/Tasks, MIST will open a browser window for Google OAuth consent. Approve access and the token will be saved to your MIST_GOOGLE_TOKEN_PATH automatically.
Mist Examples
Client configuration
Claude Desktop config block using UV to launch the MIST server with editable install.
{
"mcpServers": {
"M.I.S.T.": {
"command": "uv",
"args": [
"run",
"--with", "mcp[cli]",
"--with-editable", "/Users/you/MIST",
"mcp", "run", "/Users/you/MIST/mist/server.py"
]
}
}
}Prompts to try
Example prompts to use with MIST once it is connected to your AI assistant.
- "Search my Gmail for emails from [email protected] in the last 30 days"
- "Create a calendar event for a team standup every weekday at 9am next week"
- "Show me the git diff for my current branch and write a commit message"
- "Add a task 'Review PR #42' to my Work task list"
- "Create a note called 'meeting-notes-2026-06-16' with the action items we just discussed"Troubleshooting Mist
Google OAuth browser window does not open or authentication fails
Ensure MIST_GOOGLE_CREDENTIALS_PATH points to the correct credentials.json file downloaded from Google Cloud Console, and that the Gmail, Calendar, and Tasks APIs are enabled for that project. Delete any existing token.json and retry to force a fresh OAuth flow.
Server fails to start with 'ModuleNotFoundError' or import errors
Make sure you are using Python 3.13+ and have run 'uv install' or 'pip install -e .' inside the MIST directory. When using UV in the MCP config, confirm the --with-editable path matches the exact location of your MIST clone.
Git tools return errors or cannot find the repository
The Git tools operate on the current working directory. Ensure the directory you want to manage is accessible and that git is installed and on your PATH. You may need to specify the repository path when invoking Git-related prompts.
Frequently Asked Questions about Mist
What is Mist?
Mist is a Model Context Protocol (MCP) server that mcp server empowering ai assistants with real-world capabilities: gmail, calendar, tasks, git integration, and note management. bridges ai assistants to external services through standardized protocol with secure authentication. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Mist?
Follow the installation instructions on the Mist GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Mist?
Mist works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Mist free to use?
Yes, Mist is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Mist Alternatives — Similar Communication Servers
Looking for alternatives to Mist? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Mist in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Mist?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.