Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
io.github.vitaliiserbynassisterr/agenttrust
https://github.com/vitaliiserbynassisterr/quality-oracle
STDIO
No auth required
How models use it and what it is built for.
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Groq API key for LLM judge (free tier available at console.groq.com)
Cerebras API key for LLM judge (free tier available at cloud.cerebras.ai)
MongoDB connection URL for persistent storage
Where to find authoritative docs and source for AgentTrust.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent Studio