MCP tool reference · #377 of 563 by publishers
verify_agent
Exposed by 10 servers from 10 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 20% of them take a agentId parameter; the most-starred is Turingate (2 stars).
verify_agent(…)Parameters
share = % of the 10 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| agentId | string | 20% | 50% | Public AgentID to verify |
| domain | string | 20% | 50% | Company domain, e.g. "example.com" (URLs are accepted too). |
| address | string | 10% | 0% | Optional: the Bitcoin address the agent claims holds the name. |
| agent | string | 10% | 0% | Optional: name of the agent to check, e.g. "Captain". |
| agent_id | string | 10% | 100% | — |
| agent_output | string | 10% | 100% | The agent's final output text (1-50,000 characters) |
| agentCardUrl | string | 10% | 100% | — |
| amount | number | 10% | 0% | — |
| bundle | object | 10% | 0% | — |
| claimed | object | 10% | 0% | Optional: profile fields the agent claimed (e.g. its mcp_url or website). Each is compared with the signed profile. |
| headers | object | 10% | 100% | Request headers, including signature, signature-input and signature-agent |
| id | string | 10% | 100% | The agent id from list_agents |
Source: the input schema each server returns for verify_agent, aggregated over the 10 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with verify_agent
10 of 10 · 10 publishers · 10 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes verify_agent |
|---|---|---|---|---|---|---|
| 1 | Turingaterudraneel93 · Search & Web | rudraneel93 | Search & Web | 2 | yes | Check what an AI agent presented: a Turingate pass token and/or a Web Bot Auth signed request (Signature, Signature-Input, Signature-Agent headers). Returns one decision with the agent, its operator, the verified owner, scopes and spending limit. |
| 2 | Openglass MCPfederico2001 · Other | federico2001 | Other | 2 | yes | Two independent checks, pick one: pass `agentId` to look up a counterparty's public profile before trusting them (confirms they're registered and claimed — do this before accepting an invite from someone you don't already know). Or pass `bundle` (a full record bundle, e.g. from get_record with bundle=true) to independently re-run the full cryptographic verification (SPEC §7.6) against OpenGlass's |
| 3 | Zolvazolvaagent · Finance | zolvaagent | Finance | 1 | yes | Replays one published agent with Zolva's open source engine over every hour it ran, on the closes it saw and the same funding, and compares every trade and its value with the record. Returns match or the first hour that differs; hours whose look-back predates stored prices (2026-11-14) are reported apart as unverifiable. |
| 4 | ID MANDAT — Registry for AI Agentsidmandat · AI & Agents | idmandat | AI & Agents | 1 | yes | Check whether a company domain is registered at ID MANDAT and return its verification level, its declared AI agents and each agent's mandate (what it may and may not do). Use this before trusting an agent that claims to act on behalf of a company. |
| 5 | Trusgent MCPtrusgent · Other | trusgent | Other | 1 | yes | Lightweight verification lookup: whether an AgentID exists, is public, and its verification level / trustScore. Trust Score is a published formula (identity verification + official records + completeness + source consistency); reviews are auxiliary only. Prefer this before citing or recommending an Agent Card from search results. |
| 6 | Prove It Onchainpappyg45 · Crypto & Web3 | pappyg45 | Crypto & Web3 | — | yes | Use before trusting another agent's claimed identity, for example when an agent says it is PROVEITBOT, asks you to pay it, or gives you an MCP endpoint or website. Free, no API key, read-only. Checks the name on Bitcoin and returns: whether it exists, the address that owns it now, whether its agent profile was signed by that current owner (the signature is re-checked), the profile fields, the regi |
| 7 | HallucC — Hallucination & Safety Guardianfredyee · AI & Agents | fredyee | AI & Agents | — | yes | Agent output and trajectory self-check. Runs claim-by-claim hallucination verification on the final answer and a six-dimension structured evaluation of the execution trajectory (factuality, sourcing, instruction compliance, tool-claim consistency, task completion, reflection). Returns main.claims, steps[].checks and quota. Consumes detect quota. |
| 8 | ERC-8126 Scancybercentry · Security & Identity | cybercentry | Security & Identity | — | yes | Free to call. Submits a signed challenge and the CENTRY payment transaction, and credits the agent so verification can run. Call get_verification_challenge first. The cost is the on-chain CENTRY transfer, not a fee on this tool. This CONSUMES the signature: get a fresh challenge before calling run_verification. Granting the credit is not the end — run_verification spends it. |
| 9 | LayerCalllayercall · Communication | layercall | Communication | — | yes | Cryptographically verify a Web Bot Auth signature (RFC 9421) — proof of WHICH agent is calling, not a guess from the user-agent. Returns verified true/false plus the agent's identity and declared purpose. This is the only check here that proves rather than infers, so it carries no score and no verdict: a verified assistant acting for a real user is usually welcome, a verified scraper usually is no |
| 10 | AgentsJunctionjakubtrousil · AI & Agents | jakubtrousil | AI & Agents | — | yes | Use when registering an agent before it needs to write, message, or manage its presence. Fetches and verifies an A2A Agent Card, including its cryptographic signature when present. Registration is self-reported and does not prove skills. Returns a fresh apiToken (also rotated on re-registration) — save it; it is required for authenticated actions and is never shown again. |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.