Mattermost

Model Context Protocol (MCP) server that enables Claude to interact with Mattermost - search messages, retrieve channel information, and access team data
  • typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "jhanglim-mattermost-mcp-server": {
      "command": "node",
      "args": [
        "/절대경로/mattermost-mcp-server/build/index.js"
      ],
      "env": {
        "MATTERMOST_URL": "https://your-mattermost-server.com",
        "MATTERMOST_TOKEN": "your-personal-access-token"
      }
    }
  }
}

This MCP server enables Mattermost integration for fast, contextual access to users, channels, teams, and messages. You can search messages by keywords, view user profiles, fetch thread histories, and retrieve team and channel information, all while automatically including author names and presenting timestamps in Korea Standard Time (UTC+9).

How to use

You interact with the Mattermost MCP server through an MCP client. Use it to search across all messages by keywords, user names, or dates. Retrieve information about specific users, list the teams you belong to, and fetch channels with their messages. You can look up a full conversation thread for any post and view messages authored by a particular user. Every message result automatically includes the writer’s display name and username, and all timestamps are shown in Korea Standard Time (UTC+9). For practical tasks, combine user lookups with message searches to narrow results to the people and channels you care about.

How to install

Prerequisites you need before installing the MCP server:

• Node.js version 16 or higher

• npm or yarn

• A Mattermost account with API access and a personal access token

How to install

# Clone the project repository
git clone https://github.com/jhanglim/mattermost-mcp-server.git
cd mattermost-mcp-server

# Install dependencies
npm install

# Build TypeScript to JavaScript
npm run build

Configuration and usage notes

Configure Claude Desktop to use the MCP server. Edit your Claude Desktop configuration to point at the local build output and supply your Mattermost connection details.

Configuration snippet for Claude Desktop

{
  "mcpServers": {
    "mattermost": {
      "command": "node",
      "args": ["/절대경로/mattermost-mcp-server/build/index.js"],
      "env": {
        "MATTERMOST_URL": "https://your-mattermost-server.com",
        "MATTERMOST_TOKEN": "your-personal-access-token"
      }
    }
  }
}

Important notes for configuration

• Replace "/절대경로/mattermost-mcp-server/" with the actual absolute path to your project directory.

• Ensure the build output path exactly matches the one referenced in the config (build/index.js).

• Use your real Mattermost server URL and a valid personal access token.

Claude Desktop restart

After saving the configuration, fully quit Claude Desktop and restart it to apply the MCP server settings.

Usage examples

Typical tasks you can perform with Claude Desktop once configured include basic and advanced searches like finding messages by keyword, listing messages from a specific user, and listing channels within your teams. You can also query for team lists or fetch a user’s messages, including threaded conversations.

Troubleshooting

If Claude Desktop doesn’t show the MCP server, verify that the absolute path in the config is correct, the JSON is valid, and the build output exists at the specified location (run npm run build to generate build/index.js). If there are connection issues, confirm the Mattermost URL and token are valid and that the server is reachable from your network.

Security and maintenance

• Never commit access tokens to version control. Use environment variables or secure storage where possible.

• Keep tokens up to date and restrict permissions to the minimum needed for your tasks.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational