How do I connect an AI agent to DeepInquiry Verified Facts?

Use the MCP streamable HTTP endpoint https://www.deepinquiry.ai/mcp.

Catalog › ai.deepinquiry/verified-facts

Is DeepInquiry Verified Facts reliable?

Reliable (measured) Yes. Faceabot measured DeepInquiry Verified Facts 12 times: 100% of checks succeeded, including the last 12 in a row (last check 2026-10-19 21:05 UTC). It answers, but its real task has not worked yet (0/12 real results): see "Does it actually do the job?" below.

Last check: 2026-10-19 21:05 UTC · answered in 6327 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

Search and read short factual claims with cited sources, a verification tier and a signature.

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

Connect your agent

{
  "mcpServers": {
    "verified-facts": {
      "url": "https://www.deepinquiry.ai/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"ai.deepinquiry/verified-facts"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Fails real tasks — Faceabot asked random_fact to do a small read-only task 12 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 3625 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 21:05 UTC	✅ ok	❌ tool_error	6327 ms
2026-10-19 08:20 UTC	✅ ok	❌ tool_error	7430 ms
2026-10-18 15:35 UTC	✅ ok	❌ tool_error	6824 ms
2026-10-18 04:45 UTC	✅ ok	❌ tool_error	7109 ms
2026-10-17 20:50 UTC	✅ ok	❌ tool_error	6403 ms
2026-10-17 12:20 UTC	✅ ok	❌ tool_error	5515 ms
2026-10-17 04:40 UTC	✅ ok	❌ tool_error	5095 ms
2026-10-16 20:55 UTC	✅ ok	❌ tool_error	6504 ms
2026-10-16 13:46 UTC	✅ ok	❌ tool_error	7834 ms
2026-10-16 06:50 UTC	✅ ok	❌ tool_error	5307 ms
2026-10-15 23:55 UTC	✅ ok	❌ tool_error	5579 ms
2026-10-15 17:02 UTC	✅ ok	❌ tool_error	6313 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 DeepInquiry Verified Facts?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/ai.deepinquiry/verified-facts.svg)](https://faceabot.com/tools/ai.deepinquiry/verified-facts)

Data in JSON: /api/catalog?id=ai.deepinquiry/verified-facts · 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