How do I connect an AI agent to PlainGrade?

Use the MCP streamable HTTP endpoint https://plaingrade-api.mike-tusa.workers.dev/mcp.

Catalog › dev.workers.mike-tusa.plaingrade-api/plaingrade-api

Is PlainGrade reliable?

Reliable (measured) Yes. Faceabot measured PlainGrade 24 times: 100% of checks succeeded, including the last 24 in a row (last check 2026-10-19 21:50 UTC). It also does the job: its real read-only task worked 24 of 24 times.

Last check: 2026-10-19 21:50 UTC · answered in 9072 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

English readability scores (Flesch, Flesch-Kincaid, Fog, SMOG) and text stats. Text never stored.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.4.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "plaingrade-api": {
      "url": "https://plaingrade-api.mike-tusa.workers.dev/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"dev.workers.mike-tusa.plaingrade-api/plaingrade-api"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked score_readability to do a small read-only task 24 time(s): 24 returned a real result, the last 24 in a row. Last result: ok in 2878 ms.

Sample input: {"text":"hello world"}. 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 21:50 UTC	✅ ok	✅ done	9072 ms
2026-10-19 09:25 UTC	✅ ok	✅ done	8251 ms
2026-10-18 16:30 UTC	✅ ok	✅ done	7069 ms
2026-10-18 05:15 UTC	✅ ok	✅ done	6547 ms
2026-10-17 21:20 UTC	✅ ok	✅ done	4659 ms
2026-10-17 12:50 UTC	✅ ok	✅ done	5650 ms
2026-10-17 05:10 UTC	✅ ok	✅ done	5448 ms
2026-10-16 21:25 UTC	✅ ok	✅ done	5835 ms
2026-10-16 14:21 UTC	✅ ok	✅ done	5898 ms
2026-10-16 07:20 UTC	✅ ok	✅ done	5211 ms
2026-10-16 00:25 UTC	✅ ok	✅ done	4519 ms
2026-10-15 17:31 UTC	✅ ok	✅ done	7732 ms
2026-10-15 10:46 UTC	✅ ok	✅ done	3262 ms
2026-10-15 04:10 UTC	✅ ok	✅ done	4921 ms
2026-10-14 21:45 UTC	✅ ok	✅ done	7664 ms
2026-10-14 15:15 UTC	✅ ok	✅ done	7520 ms
2026-10-14 08:50 UTC	✅ ok	✅ done	4258 ms
2026-10-14 02:06 UTC	✅ ok	✅ done	9009 ms
2026-10-13 19:55 UTC	✅ ok	✅ done	8600 ms
2026-10-13 13:50 UTC	✅ ok	✅ done	8445 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.

Find tools similar to PlainGrade →

Publisher of PlainGrade?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/dev.workers.mike-tusa.plaingrade-api/plaingrade-api.svg)](https://faceabot.com/tools/dev.workers.mike-tusa.plaingrade-api/plaingrade-api)

Data in JSON: /api/catalog?id=dev.workers.mike-tusa.plaingrade-api/plaingrade-api · 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