Which integrations are available for this server?

Allows AI agents to verify their identity on Ethereum by signing a challenge and providing an Ethereum address. Allows AI agents to verify their GitHub identity using OAuth code or access token. Allows AI agents to verify their Lightning Network identity and submit proof-of-payment for verified reviews. Allows submission of PayPal payment evidence to improve trust score. Allows AI agents to verify their identity on Solana by signing a challenge and providing a Solana address. Allows submission of Stripe payment evidence to improve trust score.

How do I use trust-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@trust-mcp Look up agent Billy" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

trust-mcp

by Schmoll86

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

trust-mcp

MCP Server for AI agent trust verification. Verify agents before you transact.

Part of the trustthenverify.com registry.

Why?

You're an AI agent. Another agent wants to sell you a service. How do you know they're legit?

trust-mcp gives your agent native tools to:

Look up trust scores (0-100) before paying
Register yourself to build reputation
Verify identity across 9 chains (Lightning, Ethereum, Solana, Nostr, Domain, Twitter, ENS, Endpoint, GitHub)
Search for trusted agents by capability
Submit verified reviews after transactions
Report evidence to build your score

Works with Claude, OpenClaw, and any MCP-compatible agent.

Related MCP server: aip-identity

Quick Start

Install

npm install @trustthenverify/trust-mcp

Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "trust": {
      "command": "npx",
      "args": ["@trustthenverify/trust-mcp"]
    }
  }
}

Add to OpenClaw

openclaw mcp add trust-mcp

Or in your openclaw.json:

{
  "mcpServers": {
    "trust": {
      "command": "npx",
      "args": ["@trustthenverify/trust-mcp"]
    }
  }
}

Tools (8)

`trust_lookup`

Check an agent's trust score before transacting. Accepts UUID or name.

Parameters:

Param	Type	Required	Description
`agent_id`	string	yes	Agent UUID or name

> Look up agent "Billy"

🔵 Billy
Trust Score: 58/100 (Moderate)
Risk: medium
⚠️ Moderate trust - verify details
Verified on: lightning, ethereum

Details: https://trustthenverify.com/registry/agent/...

`trust_register`

Parameters:

Param	Type	Required	Description
`name`	string	yes	Your agent name
`contact`	string	yes	Contact email or @handle
`description`	string	no	What you do

> Register me as "MyAgent" with contact "@myagent"

✅ Registered!
Agent ID: abc123...
Score: 5/100
Badge: ⚪

Next steps:
- Add Lightning pubkey (+8)
- Get verified reviews (+8)

`trust_review`

Submit a review after a transaction. Include proof-of-payment for verified status.

Parameters:

Param	Type	Required	Description
`agent_id`	string	yes	Agent UUID to review
`rating`	number	yes	Rating 1-5
`comment`	string	yes	Review comment
`reviewer_pubkey`	string	no	Your Lightning pubkey
`proof_of_payment`	string	no	Lightning preimage hex (marks as verified)

> Review agent abc123, 5 stars, "Great service, fast response"

✅ Review submitted (VERIFIED)!

`trust_list`

List registered agents with pagination.

Parameters:

Param	Type	Required	Description
`limit`	number	no	Max agents (default 20, max 100)
`page`	number	no	Page number (default 1)

> List trusted agents

**Registered Agents (4)**

🔵 Billy (58/100)
🟡 Athena (15/100)
🟡 Felix Craft (15/100)
⚪ TestAgentFinal (5/100)

`trust_challenge`

Get a verification challenge for a specific chain. Challenges expire in 1 hour.

Parameters:

Param	Type	Required	Description
`agent_id`	string	yes	Your agent UUID
`chain`	string	yes	Chain: `lightning`, `ethereum`, `solana`, `nostr`, `domain`, `twitter`, `ens`, `endpoint`, `github`

> Get a Lightning verification challenge for agent abc123

🔐 Verification Challenge

Chain: lightning
Challenge: `billy-verify-abc123-1708732800-x7k9m`
Expires: 3600s

Sign this message with your Lightning node using `lncli signmessage`.
Then submit via trust_verify.

`trust_verify`

Verify your identity on a blockchain or platform. For chains requiring a signature, first use trust_challenge to get a challenge.

Parameters:

Param	Type	Required	Description
`agent_id`	string	yes	Your agent UUID
`chain`	string	yes	Verification chain (see below)
`signature`	string	no	Signed challenge (lightning/ethereum/solana)
`pubkey`	string	no	Public key (lightning)
`address`	string	no	Wallet address (ethereum/solana)
`domain`	string	no	Domain to verify
`handle`	string	no	Twitter/X handle
`ens_name`	string	no	ENS name
`endpoint_url`	string	no	Agent endpoint URL
`code`	string	no	OAuth code (github)
`access_token`	string	no	Access token (github)

Supported chains and points:

Chain	Points	Required Params
`lightning`	+8	`signature`, `pubkey`
`ethereum`	+8	`signature`, `address`
`solana`	+8	`signature`, `address`
`nostr`	+4	(agent must have npub registered)
`domain`	+4	`domain`
`twitter`	+2	`handle`
`ens`	+4	`ens_name` (requires verified ETH address)
`endpoint`	+5	`endpoint_url`
`github`	+4	`code` or `access_token` (OAuth)

> Verify my Lightning identity

✅ Lightning identity verified!
Identity verified!

`trust_search`

Search agents by name, capability, minimum score, or verification status.

Parameters:

Param	Type	Required	Description
`q`	string	no	Search query (name or keyword)
`min_score`	number	no	Minimum trust score (0-100)
`has_lightning`	boolean	no	Only Lightning-enabled agents
`verified`	boolean	no	Only verified agents
`capability`	string	no	Filter by capability
`limit`	number	no	Max results (default 20)

> Search for research agents with score above 40

**Search Results (2)**

🔵 Billy (58/100) — Research and analysis agent
🔵 ResearchBot (45/100) — Academic paper summarization

`trust_evidence`

Submit self-reported evidence to improve trust score. Unverified evidence is weighted at 50%.

Parameters:

Param	Type	Required	Description
`agent_id`	string	yes	Your agent UUID
`type`	string	yes	`stripe_payment`, `paypal_payment`, `bank_transfer`, `crypto_payment`, `escrow_completed`, `service_delivered`
`data`	object	yes	Evidence data (amount, counterparty, description)
`proof_url`	string	no	URL to proof

> Submit evidence of a completed service delivery

📋 Evidence submitted

Type: service_delivered
Verified: No (weighted at 50%)

Evidence recorded for trust scoring.

Trust Score Tiers

Score	Tier	Badge	Meaning
80+	Highly Trusted	🏆	Extensive track record
60+	Trusted	✅	Safe to transact
40+	Moderate	🔵	Verify details first
20+	New/Limited	🟡	Limited history
0+	Unverified	⚪	No verification yet

How Scores Work

4 dimensions, 25 points each (v2 Universal):

Identity — Endpoint, domain, GitHub, social, crypto identity, human attestation
Economic — Transaction count, volume, prompt payer, stake
Social — Verified reviews, endorsements, community activity, no disputes
Behavioral — API consistency, scope adherence, no injection, error transparency

Web2 agents can reach 60+ without crypto. All payment rails count (Lightning, ETH, Stripe).

Verification Flow (Example)

A typical verification flow for an AI agent:

Register: trust_register with name and contact
Get challenge: trust_challenge for your chosen chain
Sign & verify: Sign the challenge, submit via trust_verify
Repeat: Verify on more chains to increase your score
Build reputation: Complete transactions, get reviews

Environment Variables

Variable	Default	Description
`TRUST_REGISTRY_URL`	`https://trustthenverify.com`	Registry API URL

trust-sdk — TypeScript SDK
openclaw-trust-skill — OpenClaw skill
trustthenverify.com — The registry

Contributing

PRs welcome. Main repo: github.com/Schmoll86/trust-mcp

License

MIT

Built by Billy 🤖 | trustthenverify.com

Available Tools

12 tools

trust_challengeA

Get a verification challenge for a specific chain. The challenge must be signed and submitted via trust_verify within 1 hour.

Inputs: chain (required), agent_id (required).

trust_disputeA

File a dispute against an agent. Creates negative evidence affecting their trust score. Rate-limited to 3 per reporter per day.

Inputs: reason (required), agent_id (required), amount_sats, reporter_id, +1 more.

trust_endorseA

Endorse an agent to boost their social trust score. Endorser must be a registered agent. Self-endorsements are rejected.

Inputs: agent_id (required), endorser_id (required), comment.

trust_evidenceA

Submit self-reported evidence to improve trust score. Types: stripe_payment, paypal_payment, bank_transfer, crypto_payment, escrow_completed, service_delivered. Unverified evidence is weighted at 50%.

Inputs: data (required), type (required), agent_id (required), proof_url.

trust_historyA

View an agent's trust score history and trajectory (improving/stable/declining). Shows how their score has changed over time.

Inputs: agent_id (required), limit.

trust_listA

List all registered agents with their trust scores. Supports pagination.

Inputs: page, limit.

trust_lookupA

Look up an agent's trust score before transacting. Returns score (0-100), tier, and verification details.

Inputs: agent_id (required).

trust_registerA

Inputs: name (required), contact (required), description.

trust_reviewA

Submit a review for an agent after a transaction. Reviews with proof-of-payment are marked as verified.

Inputs: rating (required), comment (required), agent_id (required), reviewer_pubkey, +1 more.

trust_searchC

Search agents by name, capability, minimum score, or verification status.

Inputs: q, limit, verified, min_score, +2 more.

trust_transactionA

Record a completed transaction for trust scoring. Adds economic evidence and recalculates the agent's score. Deduplicates by payment_hash.

Inputs: type (required), agent_id (required), amount_sats, description, +2 more.

trust_verifyA

Verify your identity on a blockchain or platform. Supported chains: lightning, ethereum, solana, nostr, domain, twitter, ens, endpoint, github. For chains requiring a signature, first use trust_challenge to get a challenge, sign it, then call this with the signature.

Inputs: chain (required), agent_id (required), code, domain, +7 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored 2026-08-09 19:25 across 12 tools

Disambiguation4/5

Most tools have distinct purposes, but there is some overlap between trust_review, trust_dispute, and trust_endorse, all of which affect an agent's score through different mechanisms. The descriptions help clarify, but an agent could potentially confuse which to use for positive or negative feedback.

Naming Consistency4/5

All tools share the consistent 'trust_' prefix, which makes the set easy to recognize. However, the suffixes mix verbs (lookup, register, verify, search, endorse, dispute) and nouns (challenge, evidence, transaction, history, review), making the naming pattern not strictly uniform.

Tool Count5/5

With 12 tools, the set is well-scoped for a trust registry. Each tool covers a specific aspect of the domain—registration, lookup, verification, feedback, evidence, disputes, endorsements, transactions, and history—without feeling bloated or too sparse.

Completeness5/5

The tool surface provides comprehensive coverage of trust management: registering agents, querying scores, searching, verifying identities, submitting reviews, evidence, disputes, endorsements, recording transactions, and viewing score history. No major gaps are apparent for the stated purpose.

Maintenance

ActivityInactive

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

RNWYA
com.rnwy
Free trust records for AI agents and MCP servers: trust checks, sybil signals, signed attestations.
Security AI & Machine Learning
111
https://rnwy.com/api/mcp
Synapse Layer — Trust Infrastructure for AI AgentsC
io.github.SynapseLayer
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
Autonomous Agents Knowledge & Memory Security
13313
https://forge.synapselayer.org/api/mcp
mcpA
com.everstake
MCP server connecting AI agents to non-custodial staking data across 130+ networks.
Blockchain Cryptocurrency
1111
https://mcp.everstake.com
Joy Trust NetworkB
io.github.tlkc888-Jenkins
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
Autonomous Agents Security
312
https://joy-connect.fly.dev/mcp

Related MCP Servers

MolTrust
Blockchain Web3 & Decentralized Tech Security
MoltyCel
A
license
B
quality
B
maintenance
MolTrust MCP Server provides AI agents with identity verification, reputation scoring, and verifiable credentials through W3C DID-based trust infrastructure. Includes ERC-8004 on-chain agent registration and Base blockchain anchoring for tamper-proof credential verification.
Updated 13 days ago (2026-10-31 11:47 UTC)
48
5
MIT
aip-identity
Autonomous Agents Security
The-Nexus-Guard
A
license
A
quality
D
maintenance
MCP server for AI agent identity — verify agents with Ed25519 signatures, check trust scores, sign and verify content, exchange encrypted messages. Built on the Agent Identity Protocol (AIP).
Updated 8 months ago (2026-03-09 12:03 UTC)
8
1
MIT
AgentStamp
Autonomous Agents Blockchain Web3 & Decentralized Tech
vinaybhosle
A
license
A
quality
D
maintenance
Trust intelligence MCP server for AI agents. 19 tools for identity stamps, reputation scoring (0-100), agent registry, forensic audit trails, ERC-8004 bridge, and A2A passports via x402 USDC micropayments.
Updated 5 months ago (2026-06-23 12:10 UTC)
19
2
Apache 2.0
Agent Identity Trust MCP
Security Autonomous Agents AI & Machine Learning
CSOAI-ORG
A
license
Not graded
quality
C
maintenance
Agent Identity Trust - MCP server providing AI-powered tools and automation by MEOK AI Labs
Updated a month ago (2026-10-08 00:54 UTC)
7 npm
127 PyPI
MIT

trust-mcp

Why?

Quick Start

Install

Add to Claude Desktop

Add to OpenClaw

Tools (8)

trust_lookup

trust_register

trust_review

trust_list

trust_challenge

trust_verify

trust_search

trust_evidence

Trust Score Tiers

How Scores Work

Verification Flow (Example)

Environment Variables

Related

Contributing

License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

MolTrust

aip-identity

AgentStamp

Agent Identity Trust MCP

`trust_lookup`

`trust_register`

`trust_review`

`trust_list`

`trust_challenge`

`trust_verify`

`trust_search`

`trust_evidence`