← Index

AgentTrust

io.github.vitaliiserbynassisterr/agenttrust·v0.1.0·Other
Quality Score
89
/100

Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.

§01  Install
Claude Desktop (uvx)
{
  "mcpServers": {
    "agenttrust": {
      "command": "uvx",
      "args": [
        "mcp-agenttrust"
      ],
      "env": {
        "GROQ_API_KEY": "<your-groq_api_key>",
        "CEREBRAS_API_KEY": "<your-cerebras_api_key>",
        "MONGODB_URL": "<your-mongodb_url>"
      }
    }
  }
}
§02  Environment variables
GROQ_API_KEY
secret

Groq API key for LLM judge (free tier available at console.groq.com)

CEREBRAS_API_KEY
secret

Cerebras API key for LLM judge (free tier available at cloud.cerebras.ai)

MONGODB_URL
secret

MongoDB connection URL for persistent storage

§03  MCP Quality Score  ·  methodology
freshness
24
completeness
20
installability
25
documentation
15
stability
5
§04  Alternatives in Other