# io.tooloracle/trustlayer

- Registry name: `io.tooloracle/trustlayer` · version 1.0.0
- Categories (automatic, keyword rules): Crypto & blockchain, Finance & markets, Markets & trading, Agent payments (x402)
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.tooloracle%2Ftrustlayer
- Server page: https://mcpstation.net/s/io.tooloracle--trustlayer.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://tooloracle.io/trust/mcp/`

## Tools (as reported by the server, not verified)

- `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.
- `get\_signed\_fact`: WITHDRAWN \(2026-08-09\). This tool does not produce or verify a cryptographic signature and returns a non-success withdrawal notice. Do not rely on it for signed evidence.
- `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.
- `freshness\_guard`: Check if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold.
- `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.
- `verify\_signature`: WITHDRAWN \(2026-08-09\). This tool performs no cryptographic signature verification and returns a non-success withdrawal notice. A hash comparison is not signature verification.
- `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.
- `evidence\_anchor`: WITHDRAWN \(2026-08-09\). This tool does not submit any blockchain transaction and creates no on-chain anchor or proof; it returns a non-success withdrawal notice.
- `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.
- `trust\_status`: Trust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html