How do I connect an AI agent to Openhook?

Use the MCP streamable HTTP endpoint https://openhook.dev/mcp.

Catalog › io.github.openhook-dev/openhook-inbox

Is Openhook reliable?

Reliable (measured) Yes. Faceabot measured Openhook 18 times: 100% of checks succeeded, including the last 18 in a row (last check 2026-10-19 15:45 UTC). It also does the job: its real read-only task worked 18 of 18 times.

Last check: 2026-10-19 15:45 UTC · answered in 6410 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

Webhook, email and DNS inboxes for AI agents to capture callbacks and test integrations.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.1.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "openhook-inbox": {
      "url": "https://openhook.dev/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.openhook-dev/openhook-inbox"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked server_status to do a small read-only task 18 time(s): 18 returned a real result, the last 18 in a row. Last result: ok in 2386 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 15:45 UTC	✅ ok	✅ done	6410 ms
2026-10-19 00:45 UTC	✅ ok	✅ done	7414 ms
2026-10-18 09:31 UTC	✅ ok	✅ done	7586 ms
2026-10-18 01:35 UTC	✅ ok	✅ done	5500 ms
2026-10-17 17:25 UTC	✅ ok	✅ done	5917 ms
2026-10-17 09:20 UTC	✅ ok	✅ done	6893 ms
2026-10-17 01:25 UTC	✅ ok	✅ done	7754 ms
2026-10-16 18:15 UTC	✅ ok	✅ done	6415 ms
2026-10-16 11:10 UTC	✅ ok	✅ done	6942 ms
2026-10-16 04:15 UTC	✅ ok	✅ done	5223 ms
2026-10-15 21:20 UTC	✅ ok	✅ done	5293 ms
2026-10-15 14:26 UTC	✅ ok	✅ done	4264 ms
2026-10-15 07:45 UTC	✅ ok	✅ done	2783 ms
2026-10-15 01:15 UTC	✅ ok	✅ done	3417 ms
2026-10-14 18:50 UTC	✅ ok	✅ done	5348 ms
2026-10-14 12:15 UTC	✅ ok	✅ done	5994 ms
2026-10-14 05:51 UTC	✅ ok	✅ done	8668 ms
2026-10-13 23:01 UTC	✅ ok	✅ done	7258 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.

Find tools similar to Openhook →

Publisher of Openhook?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.openhook-dev/openhook-inbox.svg)](https://faceabot.com/tools/io.github.openhook-dev/openhook-inbox)

Data in JSON: /api/catalog?id=io.github.openhook-dev/openhook-inbox · 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