# Agent Index — GRC & Compliance

> Agent Index — GRC & Compliance is a free MCP server for security. Read-only directory of GRC and security AI agents and verified audit firms. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API
- **Website:** https://theagentindex.io
- **Repository:** https://github.com/theagentindex/agent-index-mcp
- **MCP Registry name:** io.theagentindex/agent-index
- **Categories:** security, legal and government
- **Listing updated:** 2026-11-14

## About

The server fronts an open CC BY 4.0 dataset of governance, risk, compliance and security AI agents and compliance audit firms. The site cites 450 agents, 640 firms (522 verified, 118 registry-listed) and 1,940 source links, mapped to frameworks like SOC 2, ISO 27001, HIPAA, FedRAMP, CMMC, DORA, DPDP and CERT-In.

It states every fact links to its source and unverified items are left blank. It is a directory, not a ranking, and firms listed only on a registry are not independently verified by the publisher.

Access is keyless over Streamable HTTP. Send a User-Agent header because some hosts block default Python urllib. Code is MIT; data is CC BY 4.0 with a DOI.

## Features

- **Agent search:** Find GRC agents by framework or category.
- **Auditor lookup:** Search audit firms against official registries.
- **Side-by-side compare:** compare_agents builds comparisons.
- **Alternatives:** get_alternatives suggests other listings.
- **Open dataset:** CC BY 4.0 with DOI.

## Good for

- Shortlist SOC 2 tooling
- Check an auditor's accreditation
- Compare agents for DORA or HIPAA
- Pull listings into an assistant

## Install

### Claude Code (Terminal)

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

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://theagentindex.io/api/mcp
```

### Cursor (~/.cursor/mcp.json)

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

### VS Code (.vscode/mcp.json)

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

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-index": {
      "serverUrl": "https://theagentindex.io/api/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

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

## Tools

- `search_agents`: Use when the user asks for AI agents or tools for a compliance, GRC or security task, or by framework. Returns the main GRC directory by default, with named agent-security products in a separate group. Pass segment=agent-security for that catalog only, or segment=all for both. Canonical theagentindex.io URLs. Not a ranking.
- `get_agent`: Use when the user names a specific agent or product and wants its listing details. Returns that one listing, with the canonical page URL, summary, frameworks, tasks and source citations.
- `search_auditors`: Use when the user asks which firms can audit or certify them (SOC 2, ISO 27001, ISO 42001, PCI DSS, HITRUST, FedRAMP, CMMC C3PAO), by country or US state, or whether a firm is accredited. Returns Verified and registry-listed firms, labelled by listing tier. Not a ranking or endorsement.
- `get_auditor`: Use when the user names a specific audit firm and wants its listing details. Returns that firm, including listing tier, the Verified flag, offices, frameworks and accreditation registry URLs.
- `compare_agents`: Use when the user names two to four agents or products and wants them compared. Returns those listings side by side and a canonical compare URL. Facts only — not a ranking or recommendation.
- `get_alternatives`: Use when the user asks for alternatives to a named vendor (e.g. Vanta, Drata). Returns the curated alternatives list for that listed agent, in the same order as /alternatives/{slug}/. Facts only — not a ranking or recommendation.

## FAQ

### Does it need authentication?

No.

### Is it a ranking?

No; the site says its criteria are not a ranking or paid placement.

### Is data reusable?

Yes under CC BY 4.0.

### Is it read-only?

Yes.

### Is Agent Index — GRC & Compliance free?

Yes. Agent Index — GRC & Compliance is free to use.

### How do I add Agent Index — GRC & Compliance to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-index https://theagentindex.io/api/mcp

### What are the best alternatives to Agent Index — GRC & Compliance?

The closest alternatives to Agent Index — GRC & Compliance are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Agent Roast](https://ai-powered.com/mcp/agent-roast): Agent Roast is an open-source MCP server for developer tools.
- [Midplane](https://ai-powered.com/mcp/midplane): Midplane is an open-source MCP server for databases.
- [Leash](https://ai-powered.com/mcp/leash): Leash is a free MCP server for security.
- [Tinplate Edge AI Safety, Security & EU Compliance](https://ai-powered.com/mcp/tinplate-edge-ai-safety-security-and-eu-compliance): Tinplate Edge AI Safety, Security & EU Compliance is a freemium MCP server for security.
- [SecureCloud](https://ai-powered.com/mcp/securecloud): SecureCloud is a free MCP server for security.
- [NY LLC Publication (FileMyPublication)](https://ai-powered.com/mcp/ny-llc-publication-filemypublication): NY LLC Publication (FileMyPublication) is a free MCP server for legal and government.
- [Eikino](https://ai-powered.com/mcp/eikino): Eikino is a freemium MCP server for security.

---
Source: https://ai-powered.com/mcp/agent-index-grc-and-compliance
