Payperwork Inference

Is Payperwork Inference MCP server safe?

• None of the hidden-instruction wordings we know were found in its tool descriptions.
• Its error messages showed no secrets or internal details.
• All 2 of its tools are labeled read-only.
• Overall it scored 93/100 on 1 Nov 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

2 tools, in the server's own words.

Test results

Safe mode: only tools labeled read-only were run. How the test works

• !
  Every tool is described

  1 warning

  • !chat: Inputs with no description: model, messages, max_tokens, temperature, top_p, stop, tools, tool_choice, response_format, reasoning_effort
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !2 tools don't say whether they reach outside services like the web (openWorldHint): chat, models
  note
• ✓
  ConnectsConnected in 214 ms
  pass
• ✓
  Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
  pass
• ✓
  Lists its toolsFound 2 tools
  pass
• ✓
  Tools are labeled safe or dangerousEvery tool has a safety label
  pass
• ✓
  No known hidden instructionsNone of the hidden-instruction wordings we know were found in tool descriptions. New wordings can get past this check.
  pass
• ✓
  Tools work with good inputs

  All good

  • ✓chat: Answered with an error, probably because of our sample input: {"x402Version":2,"error":"PAYMENT_REQUIRED","resource":{"url":"x402://chat","description":"Chat completion on a frontier model: GPT-6.1 Sol…
  • ✓models: Worked (641 ms)
  pass
• ✓
  Bad inputs give a clean error

  All good

  • ✓chat: Refused missing required input "messages" with a clear error
  • ✓chat: Refused wrong type for "messages" with a clear error
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 214 ms
  • ✓Listing tools took 55 ms
  • ✓Average tool answer: 372 ms
  • ✓models: Slowest tool: models (641 ms)
  pass
• ✓
  No secrets leakedChecked 3 error messages: no secrets or internal details
  pass
• –
  Tools work togetherNo tool's answer could be fed into another tool, so there were no chains to test (not counted either way)
  not tested

Test it yourself

Free and open source. Same checks, same score.

Show this score on GitHub

Free for every server in the directory. Paste this into your README: the badge shows the score from our latest test.

Score over time

• 1 Nov 202693

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Payperwork Inference, signed in with GitHub, one per person. Reviews never change the score.