How do I connect an AI agent to AI Benchmark Index?

Use the MCP streamable HTTP endpoint https://aibenchmarkindex.com/mcp.

Catalog › com.aibenchmarkindex/directory

Is AI Benchmark Index reliable?

Reliable (measured) Yes. Faceabot measured AI Benchmark Index 10 times: 100% of checks succeeded, including the last 10 in a row (last check 2026-10-19 12:10 UTC). It also does the job: its real read-only task worked 10 of 10 times.

Last check: 2026-10-19 12:10 UTC · answered in 6773 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Search 264 AI benchmarks by category, with data sources and licences for each.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "directory": {
      "url": "https://aibenchmarkindex.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.aibenchmarkindex/directory"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked get_stats to do a small read-only task 10 time(s): 10 returned a real result, the last 10 in a row. Last result: ok in 2745 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 12:10 UTC	✅ ok	✅ done	6773 ms
2026-10-18 20:00 UTC	✅ ok	✅ done	7485 ms
2026-10-18 07:00 UTC	✅ ok	✅ done	6705 ms
2026-10-17 23:10 UTC	✅ ok	✅ done	5233 ms
2026-10-17 15:00 UTC	✅ ok	✅ done	6805 ms
2026-10-17 06:55 UTC	✅ ok	✅ done	4897 ms
2026-10-16 23:05 UTC	✅ ok	✅ done	6287 ms
2026-10-16 15:55 UTC	✅ ok	✅ done	7206 ms
2026-10-16 08:55 UTC	✅ ok	✅ done	7142 ms
2026-10-16 02:01 UTC	✅ ok	✅ done	7236 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Publisher of AI Benchmark Index?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.aibenchmarkindex/directory.svg)](https://faceabot.com/tools/com.aibenchmarkindex/directory)

Data in JSON: /api/catalog?id=com.aibenchmarkindex/directory · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms