# trustlayer MCP server

FeedOracle Trust Layer - 10-tool cross-server trust: signing, anchoring, verification.

## Links
- Registry page: https://www.getdrio.com/mcp/io-tooloracle-trustlayer
- Repository: https://github.com/ToolOracle/trustlayer

## Install
- Endpoint: https://tooloracle.io/trust/mcp/
- Auth: Not captured

## Setup notes
- Remote endpoint: https://tooloracle.io/trust/mcp/

## Tools
- verify_claim - Verify an agent's claim against FeedOracle signed evidence. Checks if a statement (e.g. 'USDC market cap is $32B') matches live, cryptographically signed data. Returns verified/partially_verified/unverified with confidence score and recommended action. Endpoint: https://tooloracle.io/trust/mcp/
- get_signed_fact - Get a cryptographically signed, machine-verifiable fact. Returns ES256K-signed data with JWKS verification URL. Other agents can independently verify the signature. Endpoint: https://tooloracle.io/trust/mcp/
- provenance_trace - Full data provenance chain — traces every data point from external source (CoinGecko, ESMA, on-chain) through FeedOracle processing to final delivery. Each step individually hashed. Supports EU AI Act Art. 13 transparency requirements. Endpoint: https://tooloracle.io/trust/mcp/
- freshness_guard - Check if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold. Endpoint: https://tooloracle.io/trust/mcp/
- hallucination_check - Compare an agent's statement against ground truth evidence. Detects factual mismatches and dangerous hallucination patterns (absolute language, suspect claims). Returns evidence checks and red flags. Endpoint: https://tooloracle.io/trust/mcp/
- verify_signature - Verify a JWS or DSSE signature from FeedOracle evidence. Confirms cryptographic integrity and origin authenticity. Public JWKS at /.well-known/jwks.json. Endpoint: https://tooloracle.io/trust/mcp/
- confidence_gate - Decision gate for agents: should I proceed, exercise caution, abstain, or escalate? Evaluates multi-factor confidence for a specific action type (cite, trade, report, recommend) against a threshold. Endpoint: https://tooloracle.io/trust/mcp/
- evidence_anchor - Anchor a fact on-chain (Polygon) as immutable, timestamped evidence. Creates an append-only registry entry with pack_id and content hash. Tamper-proof audit trail. Endpoint: https://tooloracle.io/trust/mcp/
- agent_reputation - Get trust score and reputation for an AI agent from FeedOracle KYA (Know Your Agent) system. Returns trust level (UNVERIFIED → CERTIFIED), score (0-100), and registration details. Endpoint: https://tooloracle.io/trust/mcp/
- trust_status - Trust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do. Endpoint: https://tooloracle.io/trust/mcp/

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.tooloracle
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 7, 2026
- Source: https://registry.modelcontextprotocol.io