Trustlayer
by tooloracle.io in Security & trust
FeedOracle Trust Layer - 10-tool cross-server trust: signing, anchoring, verification.
https://tooloracle.io/trust/mcp/- Tools
- 10
- open to any client
- Uptime
- 94.4%
- last 30 days
- Response time
- 112 ms
- 224 ms slowest 5%
- Last check
- Passed
- 8 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to connect
Add it to any MCP client that supports remote servers.
{
"mcpServers": {
"trustlayer-2": {
"type": "http",
"url": "https://tooloracle.io/trust/mcp/"
}
}
}10 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.
- 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WITHDRAWN (2026-08-09).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 Prevents agent decisions based on outdated information.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WITHDRAWN (2026-08-09).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WITHDRAWN (2026-08-09).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.
Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time |
|---|---|---|---|
| 8 h ago | Passed | 200 | 101 ms |
| 19 h ago | Passed | 200 | 121 ms |
| 30 h ago | Passed | 200 | 171 ms |
| 40 h ago | Passed | 200 | 112 ms |
| 2 days ago | Passed | 200 | 100 ms |
Show 10 older checks
| 3 days ago | Passed | 200 | 96 ms |
| 3 days ago | Passed | 200 | 143 ms |
| 3 days ago | Passed | 200 | 113 ms |
| 4 days ago | Passed | 200 | 123 ms |
| 4 days ago | Passed | 200 | 98 ms |
| 5 days ago | Passed | 200 | 135 ms |
| 5 days ago | Passed | 200 | 35 ms |
| 5 days ago | Passed | 200 | 101 ms |
| 6 days ago | Passed | 200 | 191 ms |
| 6 days ago | Passed | 200 | 30 ms |