AgentTrust MCP Server

What the code does

We read the source, 7 d ago · rules 3dff92dd89df

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

        result = eval(expression)  # noqa: S307

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add agenttrust -- uvx mcp-agenttrust

{
  "mcpServers": {
    "agenttrust": {
      "args": [
        "mcp-agenttrust"
      ],
      "command": "uvx"
    }
  }
}

[mcp_servers.agenttrust]
command = "uvx"
args = ["mcp-agenttrust"]

{
  "mcpServers": {
    "agenttrust": {
      "args": [
        "mcp-agenttrust"
      ],
      "command": "uvx"
    }
  }
}

{
  "mcpServers": {
    "agenttrust": {
      "args": [
        "mcp-agenttrust"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: GROQ_API_KEY (Groq API key for LLM judge (free tier available at console.groq.com)), CEREBRAS_API_KEY (Cerebras API key for LLM judge (free tier available at cloud.cerebras.ai)), MONGODB_URL (MongoDB connection URL for persistent storage). The author declared them in the registry entry; get the values from the project itself.