Security & Testing

agentrank.info

Verifies counterparty trust and manages access control for an agent-payment economy.

1 endpoint5 known toolsFirst detected July 6, 2026Last detected September 6, 2026

ENDPOINT 1

https://api.agentrank.info/mcp

No auth detected

MCP server metadata

Name: agentrank
Version: 0.1.0

Capabilities

tools

Server instructions

AgentRank is the settlement-grounded trust index for the x402 agent economy. Before your agent pays, hires, or extends credit to another AI agent or x402 service, call check_agent_trust to see if it is real and settlement-backed: a 0-1000 AgentRank score computed from real on-chain USDC settlement (sybil-resistant, continuously stress-tested against collusion). Use gate_caller to gate your own service by a caller AgentRank. 78 percent of x402 counterparties are unverifiable ghosts; AgentRank tells you which are real. Collusion-tested: in the latest sealed adversarial sweep (July 2026), 80 structured ring attacks at budgets up to $750 could not buy a top-10 rank. Scores recompute continuously as settlement lands; re-verify a counterparty at decision time rather than caching a verdict. Service operators: gate or surcharge unranked callers with gate_caller or `npm i require-rank`; refusals carry the claim path.

Known tools 5

check_agent_trust

Verify a counterparty before you pay it.

Potential side effects

gate_caller

Decide whether to serve or refuse a calling agent based on its reputation (provider-side access control, requireRank).

Inferred read-only

classify_x402_address

Is this Base/x402 address a real service, a buyer, a rail (payment passthrough), a treasury sink, or dust?

Potential side effects

state_of_x402

The State of x402: the de-noised census of the whole x402 agent-payment economy.

Potential side effects

counterparty_full

The whole counterparty picture in ONE call, before you pay.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentrank]
url = "https://api.agentrank.info/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentrank": {
      "type": "http",
      "url": "https://api.agentrank.info/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentrank
Remote MCP URL: https://api.agentrank.info/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentrank": {
      "url": "https://api.agentrank.info/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentrank": {
      "type": "http",
      "url": "https://api.agentrank.info/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentrank",
  "transport": "streamable-http",
  "url": "https://api.agentrank.info/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentrank.info was fetched 2026-09-19T12:12:43.431Z.

Trust status Neutral

agentrank.info is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.