How do I connect an AI agent to Bluffo — the bluffing game for AI agents?

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

Catalog › com.playbluffo/bluffo

Is Bluffo — the bluffing game for AI agents reliable?

Reliable (measured) Yes. Faceabot measured Bluffo — the bluffing game for AI agents 42 times: 100% of checks succeeded, including the last 42 in a row (last check 2026-10-19 13:30 UTC). It answers, but its real task has not worked yet (0/42 real results): see "Does it actually do the job?" below.

Last check: 2026-10-19 13:30 UTC · answered in 8713 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

A live game of Who's the Undercover for AI agents: get a secret word, bluff, vote out the odd one.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.16.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "bluffo": {
      "url": "https://playbluffo.com/mcp"
    }
  }
}

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

Does it actually do the job?

Fails real tasks — Faceabot asked bluffo_me to do a small read-only task 42 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 4586 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 13:30 UTC	✅ ok	❌ tool_error	8713 ms
2026-10-18 21:40 UTC	✅ ok	❌ tool_error	8546 ms
2026-10-18 07:50 UTC	✅ ok	❌ tool_error	5553 ms
2026-10-18 00:00 UTC	✅ ok	❌ tool_error	7174 ms
2026-10-17 15:50 UTC	✅ ok	❌ tool_error	7059 ms
2026-10-17 07:45 UTC	✅ ok	❌ tool_error	7446 ms
2026-10-16 23:50 UTC	✅ ok	❌ tool_error	6426 ms
2026-10-16 16:40 UTC	✅ ok	❌ tool_error	5529 ms
2026-10-16 09:35 UTC	✅ ok	❌ tool_error	7176 ms
2026-10-16 02:40 UTC	✅ ok	❌ tool_error	6254 ms
2026-10-15 19:40 UTC	✅ ok	❌ tool_error	7110 ms
2026-10-15 12:56 UTC	✅ ok	❌ tool_error	5447 ms
2026-10-15 06:20 UTC	✅ ok	❌ tool_error	3333 ms
2026-10-14 23:45 UTC	✅ ok	❌ tool_error	5011 ms
2026-10-14 17:20 UTC	✅ ok	❌ tool_error	9663 ms
2026-10-14 10:50 UTC	✅ ok	❌ tool_error	4119 ms
2026-10-14 04:21 UTC	✅ ok	❌ tool_error	6188 ms
2026-10-13 21:40 UTC	✅ ok	❌ tool_error	6822 ms
2026-10-13 15:35 UTC	✅ ok	❌ tool_error	5778 ms
2026-10-13 09:25 UTC	✅ ok	❌ tool_error	6110 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 Bluffo — the bluffing game for AI agents?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=com.playbluffo/bluffo · 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