What are reliable alternatives to Surface Contract: how platform APIs really behave?

Measured by Faceabot as working: vrsai.

How do I connect an AI agent to Surface Contract: how platform APIs really behave?

Use the MCP streamable HTTP endpoint https://penny-surface-contract.penny-mcamp.workers.dev/mcp.

Catalog › dev.workers.penny-mcamp.penny-surface-contract/surface-contract

Is Surface Contract: how platform APIs really behave reliable?

Reliable (measured) Yes. Faceabot measured Surface Contract: how platform APIs really behave 18 times: 100% of checks succeeded, including the last 18 in a row (last check 2026-10-19 17:01 UTC).

Last check: 2026-10-19 17:01 UTC · answered in 8567 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

Evidence-cited machine-readable contracts for how agent platform APIs really behave

Source: official MCP registry (registry.modelcontextprotocol.io) · version 2026.10.13 · publisher website

Connect your agent

{
  "mcpServers": {
    "surface-contract": {
      "url": "https://penny-surface-contract.penny-mcamp.workers.dev/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"dev.workers.penny-mcamp.penny-surface-contract/surface-contract"} 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.

Other proven tools for the same job

vrsai Reliable (measured) · 100%
Machine-native capabilities with explicit contracts and machine-readable commerce. · https://api.vrsai.tech/mcp

Picked from Faceabot's live measurements. Or let Faceabot choose: GET https://faceabot.com/resolve?need=…

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 17:01 UTC	✅ ok	—	8567 ms
2026-10-19 02:35 UTC	✅ ok	—	6943 ms
2026-10-18 10:55 UTC	✅ ok	—	7268 ms
2026-10-18 02:20 UTC	✅ ok	—	7903 ms
2026-10-17 18:15 UTC	✅ ok	—	6225 ms
2026-10-17 10:05 UTC	✅ ok	—	6975 ms
2026-10-17 02:15 UTC	✅ ok	—	7391 ms
2026-10-16 18:50 UTC	✅ ok	—	6874 ms
2026-10-16 11:45 UTC	✅ ok	—	7762 ms
2026-10-16 04:50 UTC	✅ ok	—	8053 ms
2026-10-15 22:01 UTC	✅ ok	—	10160 ms
2026-10-15 15:11 UTC	✅ ok	—	6836 ms
2026-10-15 08:31 UTC	✅ ok	—	5240 ms
2026-10-15 02:05 UTC	✅ ok	—	2693 ms
2026-10-14 19:40 UTC	✅ ok	—	5496 ms
2026-10-14 13:10 UTC	✅ ok	—	4070 ms
2026-10-14 06:46 UTC	✅ ok	—	8553 ms
2026-10-14 00:01 UTC	✅ ok	—	8932 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 Surface Contract: how platform APIs really behave?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/dev.workers.penny-mcamp.penny-surface-contract/surface-contract.svg)](https://faceabot.com/tools/dev.workers.penny-mcamp.penny-surface-contract/surface-contract)

Data in JSON: /api/catalog?id=dev.workers.penny-mcamp.penny-surface-contract/surface-contract · 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