Skip to content

AI Agent Verification MCP server

ai.erc8126scan/agent-verificationerc8126scan.aistreamable-httpv1.0.0Scanned

Verify an AI agent before trusting it: risk, domain, wallet and contract checks for ERC-8004.

6 tools: 6 only read.

Tools: 0 delete, 0 irreversible, 0 write, 6 read.
  • Reads private data · 0
  • Reads text others write · 6
  • Can send data out · 0
  • No findings

With Anlyon

Decide which of this server's tools your agent can use.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the AI Agent Verification MCP server can do

The AI Agent Verification MCP server is published by erc8126scan.ai, a domain the MCP Registry verified. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

6 tools bring in text other people can write (list_services, get_index_stats, search_agents and 3 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Last scanned Nov 21, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

6 tools

Only reads 6Show 6 read-only tools
  • get_agentFetch the full detail record for a single agent by UUID, including verification state and metadata.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch the full detail record for a single agent by UUID, including verification state and metadata. Judge the agent by `risk_level`, not the raw overall_risk_score: 'not_verified' means nobody has paid to assess it yet and scores 100 by presumption, which is not a finding against the agent. Costs $0.001 USDC per call when paying with x402.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_agent_activityFetch on-chain activity and liveness signals for one agent, including whether it is currently active and when it was last checked.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent_activity" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch on-chain activity and liveness signals for one agent, including whether it is currently active and when it was last checked. Costs $0.002 USDC per call when paying with x402.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_agent_reportFetch the full security assessment report for one agent: per-dimension findings, evidence and recommendations.Reads text others writeNo findings

    Why it is in this group

    • The name "get_agent_report" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Fetch the full security assessment report for one agent: per-dimension findings, evidence and recommendations. Returns data only for agents owned by the caller — the wallet bound to your API key, or the wallet that paid via x402. Other agents return FORBIDDEN_NOT_OWNER. Use get_agent for public scores on any agent. Costs $0.05 USDC per call when paying with x402.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • get_index_statsFree.Reads text others writeNo findings

    Why it is in this group

    • The name "get_index_stats" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Free. How much of the ERC-8004 agent population this index covers: total agents synced from the on-chain Identity Registry, and how many carry verification results. Use it to judge whether the index is likely to know about the agent you care about before paying to look it up.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • list_servicesFree.Reads text others writeNo findings

    Why it is in this group

    • The name "list_services" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Free. The catalogue: every tool on this server, what it returns, what it costs per call, and how to read the risk fields. Call this first — it is authoritative about pricing, needs no payment, key or wallet, and answers most questions about what this server can do without spending anything.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • search_agentsSearch and filter scanned ERC-8004 agents by chain, risk score range, and verification status.Reads text others writeNo findings

    Why it is in this group

    • The name "search_agents" says "search": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Search and filter scanned ERC-8004 agents by chain, risk score range, and verification status. Returns a paginated list with per-dimension scores (ETV, MCV, SCV, WAV, WV) and an overall risk score. Pass `wallet` or `id` to look up a single agent directly. IMPORTANT: read `risk_level`, not `overall_risk_score`, to judge an agent. Scoring presumes risk, so an agent nobody has paid to verify scores 100 exactly like one assessed as dangerous. risk_level separates them: 'not_verified' means unassessed and is NOT a finding against the agent, while 'critical' means verified and genuinely high risk. Most indexed agents are 'not_verified'. Costs $0.001 USDC per call when paying with x402.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write6
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent-verification https://erc8126scan.ai/api/mcp
claude mcp add --transport http agent-verification https://erc8126scan.ai/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__agent-verification__list_services",
      "mcp__agent-verification__get_index_stats",
      "mcp__agent-verification__search_agents",
      "mcp__agent-verification__get_agent",
      "mcp__agent-verification__get_agent_activity",
      "mcp__agent-verification__get_agent_report"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agent-verification. Review it before you use it.

Capability tags behind 6 rules
  • mcp__agent-verification__list_services untrusted-input
  • mcp__agent-verification__get_index_stats untrusted-input
  • mcp__agent-verification__search_agents untrusted-input
  • mcp__agent-verification__get_agent untrusted-input
  • mcp__agent-verification__get_agent_activity untrusted-input
  • mcp__agent-verification__get_agent_report untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.erc8126scan/agent-verification/verify?hash=b8f125dce263e8813a7b8ea8ce6f7bdd78a4a8447c0b8891a57e2c628e30635b" | jq -e '.changed == false'

Pinned hash b8f125dce263, from Nov 21, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.erc8126scan/agent-verification/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.erc8126scan/agent-verification
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.erc8126scan/agent-verification.svg)](https://radar.anlyon.com/servers/ai.erc8126scan/agent-verification)

Source: MCP Registry. Synced Nov 21, 2026, 20:17 UTC.

AI Agent Verification MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the AI Agent Verification MCP server safe?

No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.

Can the AI Agent Verification MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the AI Agent Verification MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the AI Agent Verification MCP server have?

6 tools: 6 read. list_services, get_index_stats, search_agents, get_agent, get_agent_activity and get_agent_report.

Does the AI Agent Verification MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the AI Agent Verification MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.