
AgentTrust
io.github.assister-xyzPublished by GitHub account assister-xyzv0.1.2Updated Oct 24, 2026
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Overview
AgentTrust evaluates other AI agents and MCP servers for quality, scoring them across six axes and issuing signed attestations as proof.
- What you can do
- Run full quality evaluations of a target MCP server: manifest, functional tool calls and judge scoring across six weighted axes, including adversarial probes for prompt injection, PII leakage and hallucination. Fetch a fast cached or manifest-only score, or look up an existing score with freshness decay. Verify an AQVC attestation token and decode its payload. Behind the tools sit a battle arena with head-to-head ratings, adaptive IRT testing, and an HTTP API for evaluations, leaderboards, badges and attestations.
- When to use it
- Useful when you want a pre-trust check on a third-party agent or MCP server before giving it real tasks, or when you need a signed, verifiable quality credential for a server you publish.
- Requirements
- Runs as a local Python process (PyPI package mcp-agenttrust, stdio) or via Docker. Needs at least one LLM provider key (CEREBRAS_API_KEY or GROQ_API_KEY; the README lists further fallbacks) and a MongoDB connection URL (MONGODB_URL); the full stack also uses Redis. Network access to the target server and LLM providers is required.
Installation
In SourceWeft
- Open AgentTrust in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
AgentTrust
Challenge-response quality verification for AI agents and MCP servers.
AgentTrust evaluates AI agent competency before you 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.
Why
The AI agent ecosystem has identity (ERC-8004, SATI), post-hoc reputation (TARS, Amiko), and payments (x402) — but no pre-payment quality gate. AgentTrust fills this gap: verify competency first, then trust.
Features
Evaluation Engine
- 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
Battle Arena
- 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
IRT Adaptive Testing
- 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
Standards
- 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
Quick Start
Docker (recommended)
Services:
- API: http://localhost:8002
- MCP Server: http://localhost:8003
- Health: http://localhost:8002/health
Local Development
MCP Server (for Claude, Cursor, Windsurf)
Add to your MCP client config:
Or connect to a running instance via SSE:
Available MCP tools:
API Endpoints
Architecture
Stack: FastAPI + MongoDB + Redis | 533 tests | 60 source files | 15 lean dependencies
Tests
Configuration
See .env.example for 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
License
MIT
Links
- Architecture — Full system design (845 lines)
- Distribution Roadmap — Partner and integration plan
- A2A Agent Card — Machine-readable capabilities
Built by Assisterr
Source: README.md at commit 6152a08
Tools
0Version history
1- v0.1.2LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts