# AI Benchmark Index MCP server

> Search and compare 264 AI benchmarks by category, with data sources, licences and score provenance.

- Listing: https://mcp.tc/i/ai-benchmark-index
- Connect: use the server's own URL `https://aibenchmarkindex.com/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: AI Benchmark Index
- Homepage: <https://aibenchmarkindex.com/>

## About

Connects to the AI Benchmark Index, a catalog of AI and LLM benchmarks with source-linked facts about data, grading and reported scores. You can search benchmarks by text, place and category, fetch a single record, and see where the data comes from along with each source's licence.

It runs as a hosted Streamable HTTP endpoint at https://aibenchmarkindex.com/mcp. No sign-in or API key is needed. Results include attribution and source licence information, which should be kept when reusing the data.

## What it can do

- Search benchmarks by text, category and place
- Get a full benchmark record by slug
- List categories with benchmark counts
- List places that have benchmarks
- View index statistics and last data change
- List data sources with licence and refresh info

## Tools (6)

- `search_listings`: Search published benchmarks by text, place and category. (read-only)
- `get_listing`: Get one published benchmark by its slug. (read-only)
- `list_places`: List countries, regions and cities that have benchmarks. (read-only)
- `list_categories`: List categories with their benchmark counts. (read-only)
- `get_stats`: Get counts of benchmarks, places and categories, and when data last changed. (read-only)
- `list_sources`: List data sources with the licence and refresh of each. (read-only)

## Example prompts

- "Find agent benchmarks in the AI Benchmark Index."
- "Show details for the AgentDojo benchmark, including its data licence."
- "Which categories have the most AI benchmarks?"
- "Where does the benchmark data come from and under what licences?"

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http ai-benchmark-index https://aibenchmarkindex.com/mcp
```

2. Start Claude Code and type `/mcp`. **ai-benchmark-index** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Customize → Connectors**, click **+ Add**, then **Add custom connector**.

2. Name it **AI Benchmark Index** and paste this URL:

```url
https://aibenchmarkindex.com/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=AI%20Benchmark%20Index&connectorUrl=https%3A%2F%2Faibenchmarkindex.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://aibenchmarkindex.com/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://aibenchmarkindex.com/mcp` as the server URL and choose **No authentication**.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=ai-benchmark-index&config=eyJ1cmwiOiJodHRwczovL2FpYmVuY2htYXJraW5kZXguY29tL21jcCJ9>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "ai-benchmark-index": {
      "url": "https://aibenchmarkindex.com/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=ai-benchmark-index&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Faibenchmarkindex.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"ai-benchmark-index","type":"http","url":"https://aibenchmarkindex.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "ai-benchmark-index": {
      "type": "http",
      "url": "https://aibenchmarkindex.com/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "ai-benchmark-index": {
      "serverUrl": "https://aibenchmarkindex.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add ai-benchmark-index --url https://aibenchmarkindex.com/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.ai-benchmark-index]
url = "https://aibenchmarkindex.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http ai-benchmark-index https://aibenchmarkindex.com/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "ai-benchmark-index": {
      "type": "http",
      "url": "https://aibenchmarkindex.com/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://aibenchmarkindex.com/mcp`.

## Recent changes

- 2026-10-21 16:46 UTC: Server instructions changed. Source: automatic check. Worth a look: new server instructions.
- 2026-10-20 22:38 UTC: Server instructions changed. Source: automatic check. Worth a look: new server instructions.
- 2026-10-16 04:20 UTC: Tracking started: 6 tools read. Source: automatic check.

More on the History tab, with descriptions before and after for the newest entries: https://mcp.tc/i/ai-benchmark-index#history (Atom feed: https://mcp.tc/i/ai-benchmark-index/history.xml). It records what mcp.tc's anonymous checks saw, every 3 hours where the tool list can be read without sign-in; it is not a security review.

## Details

- Server version: 1
- MCP protocol version: 2025-06-18
- Last checked: 2026-10-24 (reachable)
- Listed: 2026-10-16
- Updated: 2026-10-16

---
Source: https://mcp.tc/i/ai-benchmark-index (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report