Agentradar Verify

@Bichev

About Agentradar Verify

Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agentradar": {
      "command": "npx",
      "args": [
        "-y",
        "@agentradar/mcp"
      ],
      "env": {
        "AGENTRADAR_API_URL": "https://api.vvpro.ai"
      }
    }
  }
}

Tools

Run a full 6-signal trust verification on an AI agent or wallet address. Returns composite trust score (0-100), individual signal scores, risk flags, and recommendations. Use this before transacting with or delegating to an unknown agent.

Compare two AI agents side-by-side on trust scores and security signals. Useful for choosing between competing agents that offer similar capabilities.

Verify multiple AI agent addresses in a single call (max 10). Returns trust scores for each address. Efficient for evaluating a list of candidate agents.

Get a cached trust score for an AI agent address. Faster than full verification — returns the last computed score without re-running signals. Free endpoint, no payment required.

Generate a trust badge URL for an AI agent. Returns an embeddable SVG badge showing the agent's trust score. Useful for displaying trust status in UIs or documentation.

Score an AI agent and write an on-chain EAS attestation recording the trust score permanently. Costs $5 via x402 or requires an operator key. Use when you need a verifiable, immutable trust record for an agent.

List all on-chain trust attestations written by AgentRadar. Returns paginated attestation records including addresses, scores, and transaction hashes. Requires operator key.

Look up a specific attestation by its transaction hash. Returns the full attestation record including the scored address, trust score, and on-chain details.

Look up an AI agent's on-chain identity (ERC-8004 registration, ENS name, contract metadata). Returns who the agent claims to be and whether those claims are verified.

Look up an AI agent's on-chain reputation — ERC-8004 feedback history, attestation count, and community signals. Shows how established and trusted the agent is in the ecosystem.

Resolve an agent address to its registered URI, metadata, and service endpoints. Useful for discovering how to interact with a verified agent.

Check if a wallet address is in the AgentRadar scam database. Returns matching scam records with severity, chain, source, and notes. Use this as a quick safety check before any transaction.

Report a malicious wallet address to the AgentRadar scam database. Requires operator key. Include chain, severity level, source of intel, and optional notes.

Get a human-readable explanation of an agent's trust score. Returns a narrative breakdown of each signal's contribution, risk factors, and actionable recommendations. Best for presenting trust analysis to end users.

Check AgentRadar API health and connectivity status. Returns service status, uptime, and version info. Use to verify the API is reachable before making other calls.

Get AgentRadar dashboard statistics — total verifications, attestations written, scam wallets tracked, and API usage metrics. Requires operator key.

List all trust scoring signals used by AgentRadar with their weights and descriptions. Helps understand how the composite trust score is calculated.

Get AgentRadar API pricing information. Shows costs for each endpoint including x402 micropayment amounts and free tier details.

Overview

What is Agentradar Verify?

Agentradar Verify is an MCP server that provides 18 tools for verifying, scoring, and attesting AI agent trustworthiness directly from Claude, Cursor, or any MCP-compatible client. It is a thin, MIT-licensed client wrapper around the public AgentRadar API, described as the on-chain trust oracle for the agent economy.

How to use Agentradar Verify?

Install and configure via npx or local build. In Cursor, add a stanza to .cursor/mcp.json using command "npx -y @agentradar/mcp" with the optional AGENTRADAR_OPERATOR_KEY environment variable. For Claude Desktop, add the same entry to claude_desktop_config.json. Run directly with npx @agentradar/mcp or clone, install, build, and run from source.

Key features of Agentradar Verify

Full 6‑signal trust verification
Side‑by‑side comparison of two agents
Batch verify up to 10 agents at once
Generate embeddable trust badge URLs
On‑chain EAS attestation of agent scores
Scam database lookup and reporting

Use cases of Agentradar Verify

Verify an AI agent by its blockchain address
Check if a wallet address is a known scam
Compare two agents to decide which is more trustworthy
Get a human‑readable explanation of a low trust score
Write an on‑chain attestation for a verified agent

FAQ from Agentradar Verify

What is the AGENTRADAR_OPERATOR_KEY used for?

It is an optional environment variable that grants access to admin endpoints and bypasses the x402 per‑call payment for paid tools.

Are there any free tools?

Yes. get_score is always free. Other pricing: verify_agent costs $0.005 per call (or free with operator key), attest_agent costs $5.00 per attestation (or free with operator key), and admin endpoints require the operator key.

Where does the data come from?

All data is served by the live API at https://api.vvpro.ai. The server is a thin client wrapper; the full auditable source code is in the repository under the MIT license.

How do I set up the server in Cursor or Claude Desktop?

Add a JSON entry to the corresponding MCP configuration file. The command is npx -y @agentradar/mcp, and you can optionally set the AGENTRADAR_OPERATOR_KEY environment variable.

Is there a limit on how many agents I can verify at once?

The batch_verify tool accepts up to 10 agents per call.

Frequently asked questions

What is the AGENTRADAR_OPERATOR_KEY used for?

It is an optional environment variable that grants access to admin endpoints and bypasses the x402 per‑call payment for paid tools.

Are there any free tools?

Yes. `get_score` is always free. Other pricing: `verify_agent` costs $0.005 per call (or free with operator key), `attest_agent` costs $5.00 per attestation (or free with operator key), and admin endpoints require the operator key.

Where does the data come from?

All data is served by the live API at `https://api.vvpro.ai`. The server is a thin client wrapper; the full auditable source code is in the repository under the MIT license.

How do I set up the server in Cursor or Claude Desktop?

Add a JSON entry to the corresponding MCP configuration file. The command is `npx -y @agentradar/mcp`, and you can optionally set the `AGENTRADAR_OPERATOR_KEY` environment variable.

Is there a limit on how many agents I can verify at once?

The `batch_verify` tool accepts up to 10 agents per call.

Comments

Basic information

More Other MCP servers

Unity MCP ✨

justinpbarnett

Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

12.2K