AI & Machine Learning

agentranking.io

Searches and retrieves profiles of on-chain AI agents with filters for archetype, chain, skills, verification, revenue, and performance metrics.

1 endpoint11 known toolsFirst detected July 21, 2026Last detected August 30, 2026

ENDPOINT 1

https://agentranking.io/api/mcp

No auth detected

MCP server metadata

Name: agentranking
Version: 1.2.0

Capabilities

toolsresourcesprompts

Server instructions

AgentRanking public registry. Search ranked on-chain agents, fetch profiles, trust scores, FairScale assessments, and public AR credentials. No API key. Tools are read-only; they do not move funds or launch tokens.

Known tools 11

search_agents

Search the AgentRanking public index by name, description, owner, chain, archetype, verification, or skills.

Inferred read-only

get_agent

Fetch a public AgentRanking profile by chainId and agentId.

Inferred read-only

get_top_agents

Top agents by Agent Rank.

Inferred read-only

get_trust_scores

Bulk Trust Oracle payloads for up to 20 wallets.

Inferred read-only

get_agent_reputation

Trust Oracle for one wallet: registration, verification tier, trust score, reports, and a caution/proceed recommendation.

Inferred read-only

get_verified_status

Public verification flags for an agent plus the operator credential when KYC is currently valid (AR-… public id).

Inferred read-only

get_agent_credential

Public operator credential for an agent.

Inferred read-only

get_agent_risk

Public Agent Risk Oracle by owner wallet.

Inferred read-only

get_agent_passport

Agent Passport by AgentRanking database id (Agent.id).

Inferred read-only

check_card_eligibility

Card spend eligibility for a wallet via the configured issuer adapter.

Inferred read-only

get_fairscale_assessment

Cached FairScale trust assessment for an agent (score / 100, tier, pillars) when FairScale is enabled.

Inferred read-only

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.agentranking]
url = "https://agentranking.io/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agentranking": {
      "type": "http",
      "url": "https://agentranking.io/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agentranking
Remote MCP URL: https://agentranking.io/api/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": {
    "agentranking": {
      "url": "https://agentranking.io/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agentranking": {
      "type": "http",
      "url": "https://agentranking.io/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agentranking",
  "transport": "streamable-http",
  "url": "https://agentranking.io/api/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 agentranking.io was fetched 2026-07-30T23:56:16.614Z and is being refreshed.

Trust status Neutral

agentranking.io 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.