# Mattermost Mcp Host

> A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based Agent.

- **Type:** MCP server
- **Install:** `agentstack add mcp-jagan-shanmugam-mattermost-mcp-host`
- **Verified:** Pending review
- **Seller:** [jagan-shanmugam](https://agentstack.voostack.com/s/jagan-shanmugam)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jagan-shanmugam](https://github.com/jagan-shanmugam)
- **Source:** https://github.com/jagan-shanmugam/mattermost-mcp-host

## Install

```sh
agentstack add mcp-jagan-shanmugam-mattermost-mcp-host
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Mattermost MCP Host

A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based AI agent to provide an intelligent interface for interacting with users and executing tools directly within Mattermost.

## Demo

### 1. Github Agent in support channel - searches the existing issues and PRs and creates a new issue if not found
   

### 2. Search internet and post to a channel using Mattermost-MCP-server

#### Scroll below for full demo in YouTube

## Features

- 🤖 **Langgraph Agent Integration**: Uses a LangGraph agent to understand user requests and orchestrate responses.
- 🔌 **MCP Server Integration**: Connects to multiple MCP servers defined in `mcp-servers.json`.
- 🛠️ **Dynamic Tool Loading**: Automatically discovers tools from connected MCP servers and makes them available to the AI agent. Converts MCP tools to langchain structured tools.
- 💬 **Thread-Aware Conversations**: Maintains conversational context within Mattermost threads for coherent interactions.
- 🔄 **Intelligent Tool Use**: The AI agent can decide when to use available tools (including chaining multiple calls) to fulfill user requests.
- 🔍 **MCP Capability Discovery**: Allows users to list available servers, tools, resources, and prompts via direct commands.
- #️⃣ **Direct Command Interface**: Interact directly with MCP servers using a command prefix (default: `#`).

## Overview

The integration works as follows:

1.  **Mattermost Connection (`mattermost_client.py`)**: Connects to the Mattermost server via API and WebSocket to listen for messages in a specified channel.
2.  **MCP Connections (`mcp_client.py`)**: Establishes connections (primarily `stdio`) to each MCP server defined in `src/mattermost_mcp_host/mcp-servers.json`. It discovers available tools on each server.
3.  **Agent Initialization (`agent/llm_agent.py`)**: A `LangGraphAgent` is created, configured with the chosen LLM provider and the dynamically loaded tools from all connected MCP servers.
4.  **Message Handling (`main.py`)**:
    *   If a message starts with the command prefix (`#`), it's parsed as a direct command to list servers/tools or call a specific tool via the corresponding `MCPClient`.
    *   Otherwise, the message (along with thread history) is passed to the `LangGraphAgent`.
5.  **Agent Execution**: The agent processes the request, potentially calling one or more MCP tools via the `MCPClient` instances, and generates a response.
6.  **Response Delivery**: The final response from the agent or command execution is posted back to the appropriate Mattermost channel/thread.

## Setup
1.  **Clone the repository:**
    ```bash
    git clone 
    cd mattermost-mcp-host
    ```

2.  **Install:**
    *   Using uv (recommended):
        ```bash
        # Install uv if you don't have it yet
        # curl -LsSf https://astral.sh/uv/install.sh | sh 

        # Activate venv
        source .venv/bin/activate
        
        # Install the package with uv
        uv sync

        # To install dev dependencies
        uv sync --dev --all-extras
        ```

3.  **Configure Environment (`.env` file):**
    Copy the `.env.example` and fill in the values or
    Create a `.env` file in the project root (or set environment variables):
    ```env
    # Mattermost Details
    MATTERMOST_URL=http://your-mattermost-url
    MATTERMOST_TOKEN=your-bot-token # Needs permissions to post, read channel, etc.
    MATTERMOST_TEAM_NAME=your-team-name
    MATTERMOST_CHANNEL_NAME=your-channel-name # Channel for the bot to listen in
    # MATTERMOST_CHANNEL_ID= # Optional: Auto-detected if name is provided

    # LLM Configuration (Azure OpenAI is default)
    DEFAULT_PROVIDER=azure
    AZURE_OPENAI_ENDPOINT=your-azure-endpoint
    AZURE_OPENAI_API_KEY=your-azure-api-key
    AZURE_OPENAI_DEPLOYMENT=your-deployment-name # e.g., gpt-4o
    # AZURE_OPENAI_API_VERSION= # Optional, defaults provided

    # Optional: Other providers (install with `[all]` extra)
    # OPENAI_API_KEY=...
    # ANTHROPIC_API_KEY=...
    # GOOGLE_API_KEY=...

    # Command Prefix
    COMMAND_PREFIX=# 
    ```
    See `.env.example` for more options.

4.  **Configure MCP Servers:**
    Edit `src/mattermost_mcp_host/mcp-servers.json` to define the MCP servers you want to connect to. See `src/mattermost_mcp_host/mcp-servers-example.json`.
    Depending on the server configuration, you might `npx`, `uvx`, `docker` installed in your system and in path.

5.  **Start the Integration:**
    ```bash
    mattermost-mcp-host
    ```

## Prerequisites

- Python 3.13.1+
- uv package manager
- Mattermost server instance
- Mattermost Bot Account with API token
- Access to a LLM API (Azure OpenAI)

### Optional
- One or more MCP servers configured in `mcp-servers.json` 
- Tavily web search requires `TAVILY_API_KEY` in `.env` file

## Usage in Mattermost

Once the integration is running and connected:

1.  **Direct Chat:** Simply chat in the configured channel or with the bot. The AI agent will respond, using tools as needed. It maintains context within message threads.
2.  **Direct Commands:** Use the command prefix (default `#`) for specific actions:
    *   `#help` - Display help information.
    *   `#servers` - List configured and connected MCP servers.
    *   `# tools` - List available tools for ``.
    *   `# call  ` - Call `` on `` with arguments provided as a JSON string.
        *   Example: `#my-server call echo '{"message": "Hello MCP!"}'`
    *   `# resources` - List available resources for ``.
    *   `# prompts` - List available prompts for ``.

## Next Steps
- ⚙️ **Configurable LLM Backend**: Supports multiple AI providers (Azure OpenAI default, OpenAI, Anthropic Claude, Google Gemini) via environment variables.

## Mattermost Setup

1. **Create a Bot Account**
- Go to Integrations > Bot Accounts > Add Bot Account
- Give it a name and description
- Save the access token in the .env file

2. **Required Bot Permissions**
- post_all
- create_post
- read_channel
- create_direct_channel
- read_user

3. **Add Bot to Team/Channel**
- Invite the bot to your team
- Add bot to desired channels

### Troubleshooting

1. **Connection Issues**
- Verify Mattermost server is running
- Check bot token permissions
- Ensure correct team/channel names

2. **AI Provider Issues**
- Validate API keys
- Check API quotas and limits
- Verify network access to API endpoints

3. **MCP Server Issues**
- Check server logs
- Verify server configurations
- Ensure required dependencies are installed and env variables are defined

## Demos

### Create issue via chat using Github MCP server
  

### (in YouTube)
[](https://youtu.be/s6CZY81DRrU)

## Contributing

Please feel free to open a PR.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jagan-shanmugam](https://github.com/jagan-shanmugam)
- **Source:** [jagan-shanmugam/mattermost-mcp-host](https://github.com/jagan-shanmugam/mattermost-mcp-host)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-jagan-shanmugam-mattermost-mcp-host
- Seller: https://agentstack.voostack.com/s/jagan-shanmugam
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.