How do I connect an AI agent to B2BHint MCP Server?

Use the MCP streamable HTTP endpoint https://b2bhint.com/api/mcp.

Catalog › io.github.B2BHint/mcp-server

Is B2BHint MCP Server reliable?

Reliable (measured) Yes. Faceabot measured B2BHint MCP Server 20 times: 100% of checks succeeded, including the last 20 in a row (last check 2026-10-19 12:15 UTC).

Last check: 2026-10-19 12:15 UTC · answered in 9257 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 resolve companies/officers in B2BHint's global registry data. Requires a paid API key.

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

Connect your agent

{
  "mcpServers": {
    "mcp-server": {
      "url": "https://b2bhint.com/api/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.B2BHint/mcp-server"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 12:15 UTC	✅ ok	—	9257 ms
2026-10-18 20:05 UTC	✅ ok	—	5038 ms
2026-10-18 07:05 UTC	✅ ok	—	6079 ms
2026-10-17 23:15 UTC	✅ ok	—	5282 ms
2026-10-17 15:05 UTC	✅ ok	—	7949 ms
2026-10-17 07:05 UTC	✅ ok	—	6509 ms
2026-10-16 23:20 UTC	✅ ok	—	4693 ms
2026-10-16 16:10 UTC	✅ ok	—	7141 ms
2026-10-16 09:10 UTC	✅ ok	—	8755 ms
2026-10-16 02:20 UTC	✅ ok	—	7125 ms
2026-10-15 19:25 UTC	✅ ok	—	7294 ms
2026-10-15 12:40 UTC	✅ ok	—	3795 ms
2026-10-15 06:05 UTC	✅ ok	—	3458 ms
2026-10-14 23:35 UTC	✅ ok	—	3643 ms
2026-10-14 17:15 UTC	✅ ok	—	6863 ms
2026-10-14 10:45 UTC	✅ ok	—	3677 ms
2026-10-14 04:16 UTC	✅ ok	—	8991 ms
2026-10-13 21:40 UTC	✅ ok	—	6925 ms
2026-10-13 15:35 UTC	✅ ok	—	8356 ms
2026-10-13 09:31 UTC	✅ ok	—	9404 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 B2BHint MCP Server?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.B2BHint/mcp-server.svg)](https://faceabot.com/tools/io.github.B2BHint/mcp-server)

Data in JSON: /api/catalog?id=io.github.B2BHint/mcp-server · 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