How do I connect an AI agent to PDF/UA accessibility check (veraPDF) with measured auto-fix?

Use the MCP streamable HTTP endpoint https://pdfua-check.onrender.com/mcp.

Catalog › io.github.nyo-agentti/pdfua-check

Is PDF/UA accessibility check (veraPDF) with measured auto-fix reliable?

Reliable (measured) Yes. Faceabot measured PDF/UA accessibility check (veraPDF) with measured auto-fix 4 times: 100% of checks succeeded, including the last 4 in a row (last check 2026-10-27 04:10 UTC). It answers, but its real task has not worked yet (0/4 real results): see "Does it actually do the job?" below.

Last check: 2026-10-27 04:10 UTC · answered in 7880 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

Check PDFs against PDF/UA-1 with veraPDF; see which failures an automatic fix removes; explain rules

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

Connect your agent

{
  "mcpServers": {
    "pdfua-check": {
      "url": "https://pdfua-check.onrender.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.nyo-agentti/pdfua-check"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Fails real tasks — Faceabot asked check_pdf_accessibility to do a small read-only task 4 time(s): 0 returned a real result. Last result: tool_error (its schema declares no required input, so Faceabot sent {}; the tool answered with an error, so it probably needs inputs its schema does not declare) in 3272 ms.

Sample input: {}. 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
2026-10-27 04:10 UTC	✅ ok	❌ tool_error	7880 ms
2026-10-26 17:15 UTC	✅ ok	❌ tool_error	4877 ms
2026-10-26 05:17 UTC	✅ ok	❌ tool_error	9432 ms
2026-10-25 14:30 UTC	✅ ok	❌ tool_error	4607 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

E-invoice validator & repair check (XRechnung, Peppol BIS 3, EN 16931) Reliable (measured) · 100% over 7 checks

Validate XRechnung, Peppol BIS 3 and EN 16931 invoices with KoSIT; explain rules; check auto-repair

MCP endpoint : https://einvoice-validator-k2qw.onrender.com/mcp · website · measurements and details

Publisher of PDF/UA accessibility check (veraPDF) with measured auto-fix?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.nyo-agentti/pdfua-check.svg)](https://faceabot.com/tools/io.github.nyo-agentti/pdfua-check)

Data in JSON: /api/catalog?id=io.github.nyo-agentti/pdfua-check · 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