FeedOracle Trust Layer - 10-tool cross-server trust: signing, anchoring, verification.
Scored across 10 tools
The active tools are mostly distinct, but the three withdrawn tools (evidence_anchor, get_signed_fact, verify_signature) all do the same thing—return a withdrawal notice—creating ambiguity. Additionally, hallucination_check and verify_claim both compare statements against evidence and could be confused. The presence of non-functional tools pollutes the toolset.
Tool names mix descriptive compound nouns (agent_reputation, trust_status) with imperative verb phrases (verify_claim, get_signed_fact). There is no consistent verb_noun pattern, and the withdrawn tools add naming diversity without helping. All use underscores, but the grammatical structure varies.
At 10 tools, the count is within a reasonable range, but three tools are withdrawn and non-functional, so the effective tool count is 7. This padding makes the set feel slightly inflated and could mislead agents about available capabilities.
The withdrawal of get_signed_fact and evidence_anchor removes the ability to fetch or anchor signed evidence, leaving only verification. There is no way to directly retrieve signed facts or manage evidence, so the surface has significant gaps for a trust/verification domain. Active tools cover verification, reputation, freshness, provenance, and health, but miss core data access operations.
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.
Inputs: client_id, agent_name.
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.
Inputs: symbol (required), action_type, min_confidence.
WITHDRAWN (2026-08-09).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.
Inputs: fact (required), symbol, framework.
Check if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold.
Inputs: symbol, max_age_seconds.
WITHDRAWN (2026-08-09).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.
Inputs: symbol (required), fact_type.
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.
Inputs: statement (required), context.
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.
Inputs: symbol (required).
Trust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do.
Inputs: no named parameters.
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.
Inputs: claim (required), symbol.
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.
Inputs: jws, content_hash.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Neutral W3C DID/VC identity and reputation oracle for AI agents (did:key/did:web, eddsa-jcs-2022).
Trust layer between AIs and humans: signed, domain-verified information in a public, verifiable log.
XRPLOracle - 31 XRP Ledger tools: payments, DEX, AMM, hooks, NFTs, validators, DIDs.
Signed, Bitcoin-anchored observations of AI training-data disclosure; verifies silence proofs, seals
Add one secure layer between your agents and this server.