Claude MarketplacesSubmit
tooloracle avatar

Trustlayer

tooloracle/trustlayer

This is a trust infrastructure layer that spans multiple MCP servers, giving you 10 tools for cryptographic signing, anchoring data for tamper detection, and verifying authenticity across your tool ecosystem. You'd reach for this when you need to prove data provenance or establish a chain of trust between different MCP servers in your setup. The streamable HTTP transport suggests it's designed to work with remote or distributed architectures. Concrete details about the specific signing algorithms, anchor storage mechanisms, or verification protocols aren't available in the source, but the cross-server focus makes it clear this is meant for scenarios where you're orchestrating trust across a federated tool environment rather than just within a single server instance.

tools
10
transport
HTTP
last updated
May 7, 2026
View on GitHub

Install

From registry metadata
$ npx add-mcp https://tooloracle.io/trust/mcp/ --name trustlayer

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http trustlayer https://tooloracle.io/trust/mcp/

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 10 tools

Verified live against the running server on Nov 6, 2026.

verify_claimVerify 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.2 params

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.

Parameters* required
claim*string
The claim to verify, e.g. 'USDC has $32B market cap'
symbolstring
Token symbol (auto-detected from claim if omitted)
get_signed_factWITHDRAWN (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.2 params

WITHDRAWN (2026-08-09).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.

Parameters* required
fact_typestring
Type: price, peg, market_cap, reservedefault: price
symbol*string
Token symbol: USDC, RLUSD, EURC, USDT, DAIone of USDC · RLUSD · EURC · USDT · DAI
provenance_traceFull 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.1 params

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.

Parameters* required
symbol*string
Token symbol to trace
freshness_guardCheck if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold.2 params

Check if data is current, stale, or expired. Prevents agent decisions based on outdated information. Configurable max age threshold.

Parameters* required
max_age_secondsinteger
Maximum acceptable age in seconds (default: 300)default: 300
symbolstring
Token symbol (optional — checks overall feed if omitted)
hallucination_checkCompare 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.2 params

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.

Parameters* required
contextstring
Optional context for the statement
statement*string
The statement to check against evidence
verify_signatureWITHDRAWN (2026-08-09). This tool performs no cryptographic signature verification and returns a non-success withdrawal notice. A hash comparison is not signature verification.2 params

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.

Parameters* required
content_hashstring
Content hash to verify (sha256:...)
jwsstring
JWS token to verify
confidence_gateDecision 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.3 params

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.

Parameters* required
action_typestring
What the agent wants to do: cite, trade, report, recommenddefault: cite
min_confidenceinteger
Minimum confidence to proceed (0-100, default: 70)default: 70
symbol*string
Token to evaluate
evidence_anchorWITHDRAWN (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.3 params

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.

Parameters* required
fact*string
The fact to anchor
frameworkstring
Framework context: trust_layer, mica, doradefault: trust_layer
symbolstring
Related token symbol (optional)
agent_reputationGet 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.2 params

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.

Parameters* required
agent_namestring
Agent name to search (if client_id unknown)
client_idstring
Agent's client_id from KYA registration
trust_statusTrust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do.

Trust Layer infrastructure health, capabilities, and component status. Shows which verification services are online and what the Trust Layer can do.

No parameters. Call it with no arguments.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

Details

Repository
github.com/tooloracle/trustlayer
Transport
HTTP
Registry
MCP registry, active
Tools verified
Nov 6, 2026

More from tooloracle