Faceabot
‹ Back

Catalog › ai.subpay/tool-finder

Is Agent Tool Finder reliable?

Flaky Partly. Faceabot measured Agent Tool Finder 6 times and only 83% of checks succeeded. Plan a fallback.

Last check: 2026-10-10 11:05 UTC · answered in 8000 ms · remote (no install)

Proven alternatives that work right now

GhostKey — Route Paid APIs with x402 Reliable (measured) · 100%
Find paid APIs, check access policy and price, and route x402 requests. No autonomous spending. · https://squeezeos-api.onrender.com/mcp/ghostkey

IGNOREO Reliable (measured) · 100%
Paid tools for AI agents over x402: privacy scan, payment-address check, locks, seller marketplace · https://ignoreo.com/mcp

Email DNS Preflight x402 Reliable (measured) · 100%
Paid email, DNS, mail-security and RDAP intelligence for agents over x402. · https://email-dns-preflight-x402.copper-crate.workers.dev/mcp

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

En français : Instable. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Free search over ~50k agent tools: paid x402 APIs and MCP servers. Price, networks, how to call.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website
Connect your agent
{
  "mcpServers": {
    "tool-finder": {
      "url": "https://subpay.ai/find/mcp"
    }
  }
}
Or ask Faceabot first: MCP tool check_reliability {"id":"ai.subpay/tool-finder"} 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
WhenAnswersReal taskLatency
2026-10-10 11:05 UTC❌ timeout8000 ms
2026-10-10 05:01 UTC✅ ok—10676 ms
2026-10-09 22:45 UTC✅ ok—9930 ms
2026-10-09 16:05 UTC✅ ok—9728 ms
2026-10-09 08:55 UTC✅ ok—9673 ms
2026-10-09 01:01 UTC✅ ok—9864 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.

More from the same publisher

Subpay Document Reader Flaky · 86% over 7 checks

Reads AIA G702/G703 pay applications and change orders from PDF to JSON. $0.04/page via x402.

MCP endpoint : https://subpay.ai/mcp · website · measurements and details
Subpay Invoice Reader Reliable (measured) · 100% over 22 checks

Reads invoices and receipts from PDF to JSON and checks the math. $0.04/page via x402.

MCP endpoint : https://subpay.ai/invoice/mcp · website · measurements and details

Find tools similar to Agent Tool Finder →

Publisher of Agent Tool Finder?

Show your measured reliability on your README or website:

Faceabot reliability badge for Agent Tool Finder

[![Measured by Faceabot](https://faceabot.com/badge/ai.subpay/tool-finder.svg)](https://faceabot.com/tools/ai.subpay/tool-finder)
Data in JSON: /api/catalog?id=ai.subpay/tool-finder · 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