AgentVerify
Server Details
Trust checks and Data Passports: identity, co-signed receipts, scores, badges, and custody evidence.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool maps to a distinct object or question: profile vs. score (get_agent_profile explicitly excludes the trust score that trust_check returns), badge vs. passport verification, policy decisions, and pricing. The main residual confusion is among the three trust-adjacent tools (get_agent_profile, trust_check, verify_badge), but the descriptions draw clear lines between identity, score retrieval, and signature verification.
Three conventions coexist: get_<noun> (get_agent_profile, get_pricing), <noun>_check (policy_check, trust_check), and verify_<noun> (verify_badge, verify_passport). Each is readable and internally regular, but the set lacks a single predictable pattern.
Six tools is well within a sensible range for a focused verification service, and each tool covers a genuinely different query (profile, pricing, policy, trust, badge, passport). No tool looks redundant or padded.
The surface is verification-only: there is no way to register an agent, obtain the agentverify/auth signature, request a passport or badge, or check remaining free quota, so an agent must go outside the server to reach the state these tools verify. Core read/verify workflows are covered, but the lifecycle has notable dead ends.
Available Tools
6 toolsget_agent_profileAInspect
Public agent profile. Does not include the trust score. Free.
Inputs: agent_id (required).
get_pricingBInspect
Current AgentVerify prices, network, and payments mode. Free.
Inputs: no named parameters.
policy_checkCInspect
May a party do an action in a region under a passport policy? allow, deny, or indeterminate. Payment cannot change a denial.
Inputs: action (required), region (required), party_id (required), passport_id (required), +2 more.
trust_checkBInspect
Trust score for one agent. Without payment this returns an x402 PaymentRequired tool error. Retry with params._meta['x402/payment']. A registered agent can instead pass params._meta['agentverify/auth'] ({agent_id, ts, signature} over agentverify:free:v1, method MCP, path mcp:trust_check) until the daily free quota.
Inputs: agent_id (required).
verify_badgeBInspect
Check an AgentVerify trust badge against this server's Ed25519 key. Free.
Inputs: badge (required).
verify_passportAInspect
Verify a data passport's signatures, hash chain, and policy violations. Free. Custody evidence only. Residency is self-asserted unless an attestation reference was presented, and those quotes are not verified here.
Inputs: passport_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agentic identity trust: precision decisioning, cryptographic release tokens, hash-chained proof
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Free trust records for AI agents and MCP servers: trust checks, sybil signals, signed attestations.
AI-agent trust infrastructure for discovery, authority, execution, verification, and receipts.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables agents to verify packages, datasets, files, and claims before acting on untrusted data, returning an evidence report with sources, timestamps, and explicit limits rather than a simple pass/fail checkmark.MIT

emilia-mcp-serverofficial
AlicenseAqualityAmaintenanceThe accountability layer for AI agents — a named human's signed yes before an agent does anything irreversible (payment, record change, deploy), then an offline-verifiable Trust Receipt. Apache-2.0, formally verified.3550Apache 2.0- AlicenseAqualityBmaintenancealalanet-agent is the open local client of alalanet.com, the free service an AI agent asks before it installs, connects or pays. A stdio MCP server whose key stays on your machine: it signs agent passports, receipts, skill and package releases, mail and memory locally (16 tools) and checks files and agents against alalanet's public transparency log. Hosted checks: https://alalanet.com/mcp.216Apache 2.0
- AlicenseNot gradedqualityDmaintenanceTrust and reputation system for AI agents, enabling tracking, verifying, and building trust through scores, interactions, ratings, and reports.33 PyPIMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.