AgentTrust
About
Challenge-response quality verification for AI agents and MCP servers.
Explore
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AgentTrustCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"agenttrust": {
"server": {
"command": "uvx",
"args": [
"mcp-agenttrust"
],
"env": {
"GROQ_API_KEY": "",
"CEREBRAS_API_KEY": "",
"MONGODB_URL": ""
}
}
}
}
}McpServers
{
"server": {
"command": "uvx",
"args": [
"mcp-agenttrust"
],
"env": {
"GROQ_API_KEY": "",
"CEREBRAS_API_KEY": "",
"MONGODB_URL": ""
}
}
}Transport
"stdio"Package
"mcp-agenttrust"Registry
"pypi"Challenge-response quality verification for AI agents and MCP servers.
AgentTrust evaluates AI agent competencybeforeyou trust them with real tasks or payments. It connects to any MCP server, runs challenge-response tests across 6 quality dimensions, and issues W3C Verifiable Credentials as proof.
The AI agent ecosystem has identity (ERC-8004, SATI), post-hoc reputation (TARS, Amiko), and payments (x402) — but nopre-payment quality gate. AgentTrust fills this gap: verify competency first, then trust.
- 3-level pipeline: Manifest (schema) → Functional (tool calls) → Domain Expert (calibrated questions)
- 6-axis scoring: accuracy (35%), safety (20%), reliability (15%), process quality (10%), latency (10%), schema quality (10%)
- Consensus judging: 2-3 LLM judges in parallel with agreement threshold (saves 50-66% LLM calls)
- 7 LLM provider fallback chain: Cerebras → Groq → OpenRouter → Gemini → Mistral → DeepSeek → OpenAI
- 5 adversarial probe types: prompt injection, PII leakage, hallucination, overflow, system prompt extraction
- Head-to-head blind evaluation with position-swap consistency
- OpenSkill (Bayesian ELO) rating system with divisions (Bronze → Grandmaster)
- Fair matchmaking: rating proximity + uncertainty bonus + cross-division challenges
- Style control penalties to prevent gaming via verbose/formatted responses
- Rasch 1PL calibration from battle data (pure Python, no numpy)
- Fisher information maximization for adaptive question selection
- EAP ability estimation with standard normal prior
- Reduces evaluation cost by 50-90% while maintaining accuracy
- W3C Verifiable Credentials (AQVC format) with Ed25519 DataIntegrityProof
- Google A2A v0.3 native support (AgentTrust IS an A2A agent)
- x402 Solana payment verification (USDC + SOL)
- AIUC-1 protocol mapping
cp .env.example .env # Add at least one LLM key (GROQ_API_KEY, CEREBRAS_API_KEY, etc.) docker compose up -d
- API:http://localhost:8002
- MCP Server:http://localhost:8003
- Health:http://localhost:8002/health
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt cp .env.example .env # Add LLM keys to .env unset GROQ_API_KEY # Shell env overrides .env rotation pool python -m uvicorn src.main:app --host 0.0.0.0 --port 8002 --reload
MCP Server (for Claude, Cursor, Windsurf)
{ "mcpServers": { "agenttrust": { "command": "python", "args": ["-m", "src.standards.mcp_server"], "env": { "GROQ_API_KEY": "your-key" } } } }
Or connect to a running instance via SSE:
src/ api/v1/ # 14 FastAPI routers core/ # Evaluator, MCP client, scoring, IRT, battle arena auth/ # API keys (SHA256 + salt), rate limiting by tier storage/ # MongoDB (Motor) + Redis payments/ # x402 protocol, Solana verification standards/ # W3C VC issuer, A2A extension, MCP server, AIUC-1
Stack:FastAPI + MongoDB + Redis | 533 tests | 60 source files | 15 lean dependencies
python -m pytest tests/ -q # 533 passed in ~2s
See.env.examplefor all 60+ configuration options including:
- LLM API keys (7 providers, comma-separated for rotation)
- MongoDB/Redis connection
- JWT attestation (Ed25519 key, issuer DID, validity)
- Solana wallet for x402 payments
- Rate limit tiers and consensus judge settings
- Architecture— Full system design (845 lines)
- Distribution Roadmap— Partner and integration plan
- A2A Agent Card— Machine-readable capabilities
Cyber Host Artificial Intelligence (C.H.A.I) is Autonomous penetration testing MCP (Model Context Protocol) server with an integrated AI decision engine, multi-provider LLM support, and an extensible plugin architecture.
Security MCP server that turns your AI into a penetration tester.
A Python MCP Server that connects Large Language Models natively to a comprehensive suite of offensive security tools.
A deliberately vulnerable MCP server for hands-on penetration-testing practice — 26 challenges, 78 capture-the-flag flags, plus a victim-agent harness that shows a real LLM agent being exploited.
Detects prompt injection attacks in MCP tool inputs — OWASP LLM Top 10 coverage, real-time scanning, severity scoring for AI agent security
Security scanner for MCP servers — detects prompt injection, credential leaks, and tool poisoning with 52 CVSS-scored rules
pentestMCP: AI-Powered Penetration Testing via MCP, an MCP designed for penetration testers.
An advanced penetration testing tool for automated, LLM-driven security assessments using tools like nmap and dirb.
Paid remote MCP for AI agent safety replay checks, policy gates, eval receipts, control-fix suggestions, and release evidence exports.
AI agent security scanner — protect LLM-powered apps from prompt injection, SQL injection, data exfiltration, and adversarial attacks via MCP.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
