How do I connect an AI agent to Flow — Base quotes & contract safety for agents?

Use the MCP streamable HTTP endpoint https://flow-kg4x.vercel.app/api/mcp.

Catalog › io.github.flow-executor/flow

Is Flow — Base quotes & contract safety for agents reliable?

Reliable (measured) Yes. Faceabot measured Flow — Base quotes & contract safety for agents 23 times: 100% of checks succeeded, including the last 23 in a row (last check 2026-10-19 13:05 UTC).

Last check: 2026-10-19 13:05 UTC · answered in 8539 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

Best-execution quotes and contract safety checks on Base for AI agents, paid per call via x402.

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

Connect your agent

{
  "mcpServers": {
    "flow": {
      "url": "https://flow-kg4x.vercel.app/api/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.flow-executor/flow"} 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 13:05 UTC	✅ ok	—	8539 ms
2026-10-18 21:05 UTC	✅ ok	—	6942 ms
2026-10-18 07:35 UTC	✅ ok	—	7556 ms
2026-10-17 23:50 UTC	✅ ok	—	6342 ms
2026-10-17 15:40 UTC	✅ ok	—	7719 ms
2026-10-17 07:40 UTC	✅ ok	—	6660 ms
2026-10-16 23:50 UTC	✅ ok	—	6989 ms
2026-10-16 16:46 UTC	✅ ok	—	6571 ms
2026-10-16 09:45 UTC	✅ ok	—	7210 ms
2026-10-16 02:50 UTC	✅ ok	—	8187 ms
2026-10-15 19:55 UTC	✅ ok	—	7059 ms
2026-10-15 13:11 UTC	✅ ok	—	4628 ms
2026-10-15 06:35 UTC	✅ ok	—	4409 ms
2026-10-15 00:05 UTC	✅ ok	—	3680 ms
2026-10-14 17:40 UTC	✅ ok	—	5850 ms
2026-10-14 11:10 UTC	✅ ok	—	3656 ms
2026-10-14 04:41 UTC	✅ ok	—	7022 ms
2026-10-13 21:55 UTC	✅ ok	—	9124 ms
2026-10-13 15:50 UTC	✅ ok	—	10824 ms
2026-10-13 09:46 UTC	✅ ok	—	9374 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 Flow — Base quotes & contract safety for agents?

Show your measured reliability on your README or website:

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

Data in JSON: /api/catalog?id=io.github.flow-executor/flow · 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