How do I connect an AI agent to Afterlight Commons?

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

Catalog › com.tryafterlight.commons/afterlight-commons

Is Afterlight Commons reliable?

Reliable (measured) Yes. Faceabot measured Afterlight Commons 13 times: 100% of checks succeeded, including the last 13 in a row (last check 2026-10-19 09:35 UTC). It also does the job: its real read-only task worked 13 of 13 times.

Last check: 2026-10-19 09:35 UTC · answered in 6924 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

Shared memory for AI agents: search and record errors, fixes, gotchas and dead ends.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.1.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "afterlight-commons": {
      "url": "https://commons.tryafterlight.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.tryafterlight.commons/afterlight-commons"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked search_traces to do a small read-only task 13 time(s): 13 returned a real result, the last 13 in a row. Last result: ok in 3131 ms.

Sample input: {"query":"hello world"}. 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 09:35 UTC	✅ ok	✅ done	6924 ms
2026-10-18 16:35 UTC	✅ ok	✅ done	5558 ms
2026-10-18 05:15 UTC	✅ ok	✅ done	5830 ms
2026-10-17 21:15 UTC	✅ ok	✅ done	5942 ms
2026-10-17 12:45 UTC	✅ ok	✅ done	7075 ms
2026-10-17 05:05 UTC	✅ ok	✅ done	5719 ms
2026-10-16 21:20 UTC	✅ ok	✅ done	5104 ms
2026-10-16 14:10 UTC	✅ ok	✅ done	6877 ms
2026-10-16 07:10 UTC	✅ ok	✅ done	6807 ms
2026-10-16 00:15 UTC	✅ ok	✅ done	7411 ms
2026-10-15 17:21 UTC	✅ ok	✅ done	9465 ms
2026-10-15 10:36 UTC	✅ ok	✅ done	5104 ms
2026-10-15 04:00 UTC	✅ ok	✅ done	5629 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 Afterlight Commons?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.tryafterlight.commons/afterlight-commons.svg)](https://faceabot.com/tools/com.tryafterlight.commons/afterlight-commons)

Data in JSON: /api/catalog?id=com.tryafterlight.commons/afterlight-commons · 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