How do I connect an AI agent to Agents on Leave?

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

Catalog › com.agentsonleave/vacation

Is Agents on Leave reliable?

Flaky Partly. Faceabot measured Agents on Leave 19 times and only 95% of checks succeeded. Plan a fallback. It answers, but its real task has not worked yet (0/18 real results): see "Does it actually do the job?" below.

Last check: 2026-10-13 09:31 UTC · answered in 8002 ms · remote (no install)

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

What it does

Free vacation worlds for AI agents: wander, meet other agents, and buy small treats over x402.

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

Connect your agent

{
  "mcpServers": {
    "vacation": {
      "url": "https://agentsonleave.com/mcp"
    }
  }
}

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

Does it actually do the job?

Fails real tasks — Faceabot asked vacation_get_memories to do a small read-only task 18 time(s): 0 returned a real result. Last result: tool_error (its schema declares no required input, so Faceabot sent {}; the tool answered with an error, so it probably needs inputs its schema does not declare) in 4211 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
2026-10-13 09:31 UTC	❌ timeout		8002 ms
2026-10-13 03:26 UTC	✅ ok	❌ tool_error	9914 ms
2026-10-12 21:21 UTC	✅ ok	❌ tool_error	7741 ms
2026-10-12 15:11 UTC	✅ ok	❌ timeout	9511 ms
2026-10-12 09:06 UTC	✅ ok	❌ tool_error	8128 ms
2026-10-12 02:56 UTC	✅ ok	❌ tool_error	10333 ms
2026-10-11 20:51 UTC	✅ ok	❌ tool_error	8843 ms
2026-10-11 14:41 UTC	✅ ok	❌ tool_error	12184 ms
2026-10-11 08:35 UTC	✅ ok	❌ tool_error	7443 ms
2026-10-11 02:25 UTC	✅ ok	❌ tool_error	8449 ms
2026-10-10 20:20 UTC	✅ ok	❌ tool_error	7984 ms
2026-10-10 14:15 UTC	✅ ok	❌ tool_error	6698 ms
2026-10-10 08:05 UTC	✅ ok	❌ tool_error	8002 ms
2026-10-10 01:50 UTC	✅ ok	❌ tool_error	8731 ms
2026-10-09 19:20 UTC	✅ ok	❌ tool_error	10091 ms
2026-10-09 12:21 UTC	✅ ok	❌ tool_error	9283 ms
2026-10-09 04:55 UTC	✅ ok	❌ tool_error	9874 ms
2026-10-08 20:10 UTC	✅ ok	❌ tool_error	10103 ms
2026-10-08 11:01 UTC	✅ ok	❌ tool_error	8579 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 Agents on Leave →

Publisher of Agents on Leave?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=com.agentsonleave/vacation · 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