mcp -mattermost
MCP server for Mattermost — let Claude, Cursor, and other AI assistants work with channels, messages, and files
claude mcp add --transport stdio cloud-ru-tech-mcp-server-mattermost uvx mcp-server-mattermost \ --env MATTERMOST_URL="https://your-mattermost-server" \ --env MATTERMOST_TOKEN="your-bot-or-user-token"
How to use
The mcp-server-mattermost integration exposes a Mattermost-focused MCP (Model Context Protocol) server. It provides a suite of tools to manage and interact with a Mattermost workspace, including channels, messages, reactions, threads, files, users, teams, and bookmarks (where available). Once configured, you can query for channels, post messages with attachments, search messages, manage channel membership, upload files, and retrieve user or channel metadata. The Quick Start example demonstrates wiring the server into your MCP client so you can issue natural language prompts that map to the corresponding Mattermost operations, with the assistant orchestrating actions across the workspace.
To use the tools, supply the required environment variables (Mattermost instance URL and a valid token) and run the MCP server through your chosen launcher. Your prompts can leverage the listed tool names such as list_channels, post_message, search_messages, add_reaction, upload_file, and get_user to perform concrete tasks in Mattermost channels and threads. The server translates your intents into API calls to Mattermost and returns structured results that your client can present or summarize.
How to install
Prerequisites:
- Python 3.10+ installed on your system
- Access to install Python packages (pip)
- A Mattermost server and a bot/personal access token with appropriate permissions
Installation steps:
# 1) Install Python and ensure pip is up to date
python3 --version
python3 -m pip install --upgrade pip
# 2) Install uvx (the MCP transport/runner)
pipx install uvx
# If you don't have pipx, install it first:
# python3 -m pip install --user pipx
# python3 -m pipx ensurepath
# 3) Install the mcp-server-mattermost package if not already available via uvx
# (Typically the MCP server is installed in the same environment you run uvx with the command name below)
# 4) Run the server using uvx with your Mattermost config (example)
uvx mcp-server-mattermost
Note: The Quick Start example in the README shows using uvx with a package name of mcp-server-mattermost. You can also run via a package manager or Python environment that resolves the mcp-server-mattermost entry point. When using uvx, ensure your environment has access to the Mattermost instance and the required tokens via environment variables as shown in the configuration example.
Additional notes
Tips and common issues:
- Ensure MATTERMOST_URL and MATTERMOST_TOKEN are correct and have sufficient permissions for the actions you intend to perform.
- If you encounter SSL or network issues, adjust MATTERMOST_VERIFY_SSL (default true) or NETWORK settings in your environment.
- For production deployments, consider running the server in HTTP mode behind a reverse proxy and set MCP_TRANSPORT to http with proper host binding.
- When using Docker or Docker-based workflows, mount environment variables securely and avoid embedding tokens in code or config files.
- Review the Documentation URLs in the README for advanced configuration options and troubleshooting guides.
Related MCP Servers
droidmind
Control your Android devices with AI using Model Context Protocol
lc2mcp
Convert LangChain tools to FastMCP tools
macOS-Notification
macOS Notification MCP enables AI assistants to trigger native macOS sounds, visual notifications, and text-to-speech. Built for Claude and other AI models using the Model Context Protocol.
skill-to
Convert AI Skills (Claude Skills format) to MCP server resources - Part of BioContextAI
metabase-ai-assistant
🚀 The most powerful MCP Server for Metabase - 111+ tools for AI SQL generation, dashboard automation & enterprise BI. Works with Claude, Cursor, ChatGPT.
mcp -templates
A flexible platform that provides Docker & Kubernetes backends, a lightweight CLI (mcpt), and client utilities for seamless MCP integration. Spin up servers from templates, route requests through a single endpoint with load balancing, and support both deployed (HTTP) and local (stdio) transports — all with sensible defaults and YAML-based configs.