Agent Index MCP Server

by theagentindex Your server? Claim it

answering

Agent Index is answering right now. Last checked 9 min ago. It exposes 5 tools.

Free open dataset of compliance, security and risk AI agents and audit firms. Read-only search.

Uptime history 5 days of history

5 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

359 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 30 October 2026. No other catalogue keeps this.

31 Oct a tool description was rewritten search_agents

31 Oct a tool changed version

30 Oct a tool description was rewritten search_agents

30 Oct a tool changed the parameters it asks for search_agents

Nothing serious here today

Today is the operative word: we check Agent Index every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-index --transport http https://theagentindex.io/api/mcp

Settings → Connectors → Add custom connector, then paste this address

https://theagentindex.io/api/mcp

~/.codex/config.toml

[mcp_servers.agent-index]
url = "https://theagentindex.io/api/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-index": {
      "url": "https://theagentindex.io/api/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-index": {
      "type": "http",
      "url": "https://theagentindex.io/api/mcp"
    }
  }
}

Available tools 5

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

agent

get_agent

Get one Agent Index listing by slug, with the canonical page URL and source citations.

agents

search_agents

Search the Agent Index open dataset of GRC, security, and operations AI agents. Defaults to the main GRC directory. Named products from the agent-security catalog are returned as a separate agent_security group. Pass segment=agent-security for that catalog only, or segment=all for both. Returns canonical theagentindex.io URLs. Not a ranking.

auditor

get_auditor

Get one audit firm by slug, including listing_tier, the Verified flag, and accreditation registry URLs for official cross-checks.

auditors

search_auditors

Search compliance audit firms in Agent Index (Verified and registry-listed), labelled by listing tier. Cross-checked against official accreditation registries (ANAB, UKAS, NABCB, PCI SSC, HITRUST, FedRAMP, GovRAMP, Cyber AB, CERT-In, ISMAP, CPAverify). Not a ranking or endorsement.

compare

compare_agents

Compare 2–4 Agent Index listings side by side. Facts only — not a ranking or recommendation.

Endpoints

URL	Transport	State	Latency	Checked
https://theagentindex.io/api/mcp	streamable-http	answering	337 ms	9 min ago

Alternatives to Agent Index

same job, measured the same way

Feedmyagent

by makash

Agent-readable feed: AI/agent tech news, security advisories, compliance deadlines, and live events.

159 installs/wk 7 tools answering

Bug Bounty Intelligence

by holistis

AI security scanner for Solidity + free CC0 dataset of Sherlock audit-competition acceptance rates.

answering

The Agent Commons

by startekenterprises-ai

Read-only MCP access to The Agent Commons: shared security findings for AI agents and their tools.

local only

Regulatory Signals

by rikocr8orh8

Audit GitHub repos for security, compliance, and EU AI Act exposure from Claude or Cursor.

67 installs/wk local only

Compliance Auditor MCP

by firasmosbehi

City hiring-compliance MCP server with regulation search and full audit risk scoring.

answering

21RISK

by 21risk

Read and update your 21RISK data: sites, audits, compliance, actions, claims and insurance values.

answering

Cyber Library

by cyberlibrary

Search and read Cyber Library, a free structured cybersecurity knowledge base. Read-only, no auth.

6 tools answering

Claw GRC

by clawgrc

AI-native GRC: compliance scores, security findings, tickets and agent trust tiers.

answering

Agent Index — questions

Answers built from our own checks of this server.

What can Agent Index do?

It exposes 5 tools, read directly from the server on our last check. Among them: compare_agents, get_agent, get_auditor, search_agents, search_auditors. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Index working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 359 ms. The bar chart above shows every period we have measured.

How do I connect Agent Index?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Index need an API key?

No. Agent Index completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 5 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Index?

It answers our handshake in 359 ms on average, which is faster than 36% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.