How do I connect an AI agent to AgentKernel AI model data?

Use the MCP streamable HTTP endpoint https://www.agentkernel.si/mcp.

Catalog › si.agentkernel/models

Is AgentKernel AI model data reliable?

Reliable (measured) Yes. Faceabot measured AgentKernel AI model data 15 times: 100% of checks succeeded, including the last 15 in a row (last check 2026-10-19 09:15 UTC). It also does the job: its real read-only task worked 15 of 15 times.

Last check: 2026-10-19 09:15 UTC · answered in 8518 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

Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.

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

Connect your agent

{
  "mcpServers": {
    "models": {
      "url": "https://www.agentkernel.si/mcp"
    }
  }
}

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

Does it actually do the job?

Does the job (tested) — Faceabot asked find_models to do a small read-only task 15 time(s): 15 returned a real result, the last 15 in a row. Last result: ok in 2824 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 09:15 UTC	✅ ok	✅ done	8518 ms
2026-10-18 16:20 UTC	✅ ok	✅ done	7164 ms
2026-10-18 05:10 UTC	✅ ok	✅ done	5425 ms
2026-10-17 21:10 UTC	✅ ok	✅ done	7944 ms
2026-10-17 12:40 UTC	✅ ok	✅ done	8112 ms
2026-10-17 05:00 UTC	✅ ok	✅ done	6011 ms
2026-10-16 21:15 UTC	✅ ok	✅ done	4740 ms
2026-10-16 14:05 UTC	✅ ok	✅ done	6918 ms
2026-10-16 07:05 UTC	✅ ok	✅ done	6952 ms
2026-10-16 00:10 UTC	✅ ok	✅ done	7836 ms
2026-10-15 17:16 UTC	✅ ok	✅ done	9734 ms
2026-10-15 10:31 UTC	✅ ok	✅ done	4436 ms
2026-10-15 03:55 UTC	✅ ok	✅ done	3733 ms
2026-10-14 21:30 UTC	✅ ok	✅ done	7864 ms
2026-10-14 15:00 UTC	✅ ok	✅ done	5188 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 AgentKernel AI model data?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/si.agentkernel/models.svg)](https://faceabot.com/tools/si.agentkernel/models)

Data in JSON: /api/catalog?id=si.agentkernel/models · 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