VERIFIED

Mattermost MCP Host

Safety: 55/100

0.0(0)

A Mattermost integration using LangGraph to connect to multiple MCP servers, enabling AI agent interaction and tool execution within Mattermost channels.

MCP ServersFreemium

Boost this tool

Subscribe to listing upgrades or segmented pushes.

Overview

A Mattermost integration using LangGraph to connect to multiple MCP servers, enabling AI agent interaction and tool execution within Mattermost channels.

This integration offers a convenient way to interact with MCP servers through Mattermost. However, the ability of the AI agent to execute tools and the reliance on stdio connections introduce moderate risks. It is safe when MCP servers are properly configured and the agent's actions are carefully monitored. It is risky if MCP servers have vulnerabilities or the agent is given excessive autonomy.

Performance depends on the LLM provider, network latency, and the complexity of the MCP tools being executed. Consider optimizing LLM prompts and MCP server configurations for better performance.

Cost is primarily driven by LLM API usage (tokens) and the resources consumed by the MCP servers. Monitor LLM usage and optimize tool execution to minimize costs.

HybridPython29 starsMIT

Connections & Capabilities

Connects To

GitHubDockerAzure

Capabilities

ReadWriteExec

Client Compatibility

Claude Desktop

full

Cursor

untested

Windsurf

untested

VS Code (Copilot)

untested

Tools (3)

safe

echo

Echos back the message provided as an argument.

Read-only operation, no side effects.

moderate

github_create_issue

Creates a new issue in a specified GitHub repository.

Creates a new resource in an external system.

safe

web_search

Searches the internet for information based on a query.

Read-only access to public information.

Security

Auth Method

Token

Data Locality

hybrid

Scopes

post_allcreate_postread_channelcreate_direct_channelread_user

Known Risks

!Compromised Mattermost bot token could allow unauthorized access to MCP servers.
!LLM vulnerabilities could be exploited to manipulate the agent's behavior.
!Insecure MCP server configurations could expose sensitive data or allow remote code execution.
!Lack of input validation could lead to command injection vulnerabilities.

Safety Score

moderate risk

Positive

+Uses a command prefix to differentiate between agent requests and direct commands.
+Relies on configured MCP servers, limiting the scope of potential actions.
+Environment variables are used for sensitive information, reducing hardcoding.
+Dynamic tool loading allows for flexible capability discovery.

Risks

-The LangGraph agent can execute tools, potentially leading to unintended actions.
-MCP servers are connected via stdio, which may lack robust security controls.
-Incorrectly configured MCP servers could expose sensitive data or functionality.
-The agent's autonomy depends on the LLM's decision-making, which can be unpredictable.

Use Cases

Information Retrieval

-Searching for information on the internet.
-Listing available tools on MCP servers.
-Querying specific resources on MCP servers.

Task Automation

-Creating GitHub issues based on user requests.
-Executing commands on MCP servers.
-Posting updates to Mattermost channels.

Integration and Orchestration

-Connecting Mattermost to multiple MCP servers.
-Orchestrating tool execution across different servers.
-Providing a unified interface for interacting with various systems.

Customer Support

-Answering user questions using information from various sources.
-Troubleshooting issues by executing diagnostic tools.
-Providing proactive support by monitoring system health.

Who Is This For?

Best For

Teams that need to integrate Mattermost with various internal systems.
Organizations that want to automate tasks using AI agents.
Developers who want to build custom integrations with Mattermost.
Support teams looking to improve response times and efficiency.

Not Ideal For

Environments with strict security requirements and limited trust in LLMs.
Use cases that require real-time, low-latency interactions.
Organizations without the resources to properly configure and maintain MCP servers.

Autonomy & Execution

Default ModeRead and Write enabled

The agent's autonomy is determined by the LLM and the available tools. There is no built-in sandboxing or rollback support.

StatelessYes

Retry LogicNot documented

ConcurrencySingle-threaded

Production Tip

Implement robust monitoring and logging to track agent activity and identify potential issues.

FAQ

What LLM providers are supported?

Azure OpenAI is the default, but OpenAI, Anthropic Claude, and Google Gemini are also supported via environment variables.

How do I add a new MCP server?

Edit the `mcp-servers.json` file and define the connection details for the new server.

How do I call a specific tool on an MCP server?

Use the command prefix followed by the server name, 'call', the tool name, and a JSON string of arguments. Example: `#my-server call echo '{"message": "Hello MCP!"}'`

What permissions does the Mattermost bot account need?

The bot account needs `post_all`, `create_post`, `read_channel`, `create_direct_channel`, and `read_user` permissions.

How does the agent maintain context within message threads?

The integration passes the thread history to the LangGraph agent, allowing it to maintain conversational context.

Can I use this integration with self-hosted LLMs?

The integration is designed to work with cloud-based LLM providers. Integrating with self-hosted LLMs would require modifications to the code.

Is there a way to limit the tools that the agent can access?

You can control which tools are available to the agent by configuring the MCP servers and their exposed tools.

Metrics

Discovered2/14/2026

Reviews0

Saved By0 users

Related Tools

Mattermost MCP Host - AI Tool Review & Alternatives | Flaex AI