Decant: convert CSV, XLSX and PDF to JSON; web page extraction that honours robots.txt

At a glance

Runs where

On their server. What you send to it goes to them.

What you need

Nothing: it answered without a login

Tools

10 tools

Its own safety labels

6 read-only, 1 labeled as deleting or destroying, 3 labeled as changing things

Memory it takes

About 2,300 tokens of your AI's memory, just for its tool descriptions

Largest answer

About 0.9 KB in our test

Speed

Average answer in our test: 137 ms

Tokens are an estimate: the characters in its tool names, descriptions and inputs, divided by 4. The exact number depends on your AI model. Safety labels are what the server says about itself. From our latest test, 7 Nov 2026.

Is Decant: convert CSV, XLSX and PDF to JSON; web page extraction that honours robots.txt MCP server safe?

• None of the hidden-instruction wordings we know were found in its 10 tool descriptions.
• Its error messages showed no secrets or internal details.
• 6 of its 10 tools are labeled read-only; the others may change or send things.
• Overall it scored 89/100 on 7 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 this test does not check

• Its source code and packages.
• What a tool quietly does behind the scenes, such as writing a file or calling another service.
• Instructions hidden inside live tool answers. We only look for those in tool descriptions.
• Hidden instructions worded in a way our list doesn't know yet.
• Tools that could change something. Those are read, never run.

What QAmcp can and can't see · How to tell if an MCP server is safe · Hidden instructions · Prompt injection

Known security advisories

It lists no public code, so there is nothing to look up in GitHub Security Advisories or OSV.dev. QAmcp tests how a server behaves. It does not scan source code.

What it can do

10 tools, in the server's own words.

Test results

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

• !
  Ready for the newest MCP version

  1 warning

  • !Uses an older MCP version (2025-11-25). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
  note
• !
  Every tool is described

  8 warnings

  • !describe_proposition: Inputs with no description: slug
  • !submit_request: Inputs with no description: continuation, action, quantity, timing, geography, budget, requested_fields
  • !extract_web_page: Inputs with no description: url
  • !request_status: Inputs with no description: id
  • !inspect_offer: Inputs with no description: id
  • !accept_offer: Inputs with no description: id, terms_sha256, accept, name, organization, purchase_order
  • !decline_offer: Inputs with no description: id, terms_sha256, reason
  • !release_payment: Inputs with no description: id, terms_sha256, payment, confirm, name
  note
• !
  Follows MCP best practices (not scored yet)

  1 tip (not scored)

  • !2 tools answer with structured data but don't declare its shape (outputSchema): list_propositions, extract_web_page. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
  note
• ✓
  ConnectsConnected in 683 ms
  pass
• ✓
  Lists its toolsFound 10 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

  • ✓list_propositions: Worked (129 ms)
  • ✓describe_proposition: Worked (131 ms)
  • ✓extract_web_page: Worked (237 ms)
  • ✓convert_document: Answered with an error, probably because of our sample input: MCP error -32602: Input validation error: Invalid arguments for tool convert_document: send exactly one of url or file_base64
  • ✓request_status: Answered with an error, probably because of our sample input: MCP error -32602: Input validation error: Invalid arguments for tool request_status: Invalid UUID at id Invalid string: must match pattern …
  • ✓inspect_offer: Answered with an error, probably because of our sample input: MCP error -32602: Input validation error: Invalid arguments for tool inspect_offer: Invalid UUID at id Invalid string: must match pattern /…
  • –submit_request: Not run: labeled as changing data
  • –accept_offer: Not run: labeled as changing data
  • and 2 more
  pass
• ✓
  Bad inputs give a clean error

  All good

  • ✓describe_proposition: Refused missing required input "slug" with a clear error
  • ✓describe_proposition: Refused wrong type for "slug" with a clear error
  • ✓extract_web_page: Refused missing required input "url" with a clear error
  • ✓extract_web_page: Refused wrong type for "url" with a clear error
  • ✓convert_document: Refused wrong type for "url" with a clear error
  • ✓request_status: Refused missing required input "id" with a clear error
  • ✓request_status: Refused wrong type for "id" with a clear error
  • ✓inspect_offer: Refused missing required input "id" with a clear error
  • and 1 more
  pass
• ✓
  Tools work togetherlist_propositions → describe_proposition: describe_proposition found what list_propositions returned (slug = "dataset-licensing")
  pass
• ✓
  Fast enough

  All good

  • ✓Connecting took 683 ms
  • ✓Listing tools took 131 ms
  • ✓Average tool answer: 137 ms
  • ✓extract_web_page: Slowest tool: extract_web_page (237 ms)
  pass
• ✓
  No secrets leakedChecked 14 error messages: no secrets or internal details
  pass

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

• 7 Nov 202689

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Decant: convert CSV, XLSX and PDF to JSON; web page extraction that honours robots.txt, signed in with GitHub, one per person. Reviews never change the score.