QAmcp

Copied. Paste it into Claude Code, Cursor or Codex:Fetch and follow the instructions at https://qamcp.dev/setup.md to test my MCP server.

Your AI finds your server in your project, tests it with QAmcp, explains what's wrong in plain words, fixes it with your OK, and tests again. Read the instructions

NewYour score can change any day. QAmcp Monitor keeps testing your server and emails you when it breaks. Free for 1 server.See what Monitor does →

Directory / Tolca

Tolca

Q: Is Tolca MCP server safe?

QAmcp's test on 9 Nov 2026: None of the hidden-instruction wordings we know were found in its 15 tool descriptions. Its error messages showed no secrets or internal details. All 15 of its tools are labeled read-only. Overall it scored 88/100 on 9 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.

by tolca.tonbot.ca · https://tolca.tonbot.ca/mcp

Web search + clean page text with sha256 proof, and company, sanctions and licence checks (x402)

15 tools✓ all read-only✓ no account neededPricing: not listed

Visit website

88 /100

PASS · WITH NOTES

11 of 11 checks · 9 Nov 2026

Test it now for current results

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: 15 tools
Its own safety labels: 15 read-only
Memory it takes: About 5,300 tokens of your AI's memory, just for its tool descriptions
Largest answer: About 0.8 KB in our test
Tools that look alike: 1 pair of tools with nearly the same description, so the AI may pick the wrong one
Speed: Average answer in our test: 170 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, 9 Nov 2026.

Is Tolca MCP server safe?

None of the hidden-instruction wordings we know were found in its 15 tool descriptions.
Its error messages showed no secrets or internal details.
All 15 of its tools are labeled read-only.
Overall it scored 88/100 on 9 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

None found in GitHub Security Advisories on 9 Nov 2026.

That means none were published there, not that there are no problems. QAmcp tests how a server behaves. It does not scan source code.

What it can do

15 tools, in the server's own words.

pkg_checkread-only

npm dependency risk and PyPI package safety check: is this package safe to install?

qc_contractor_checkread-only

Quebec contractor check before hiring, paying or subcontracting a Québec (Canada) construction contractor, in one call: RBQ licence (status, categories, restri…

summarizeread-only

Summarize text (up to 40k chars) into a faithful, tight summary, with optional max_words and target language.

translateread-only

Translate text between French (including Quebec French) and English, with optional tone.

extractread-only

Turn messy text into clean JSON matching the schema you provide (field names and types).

extract_urlread-only

Fetch a public URL (HTML article, PDF, or JSON) and return JSON matching your schema in one call, with page title and source.

qc_licenceread-only

Quebec contractor licence check (RBQ): contractor license verification in one call, cheapest tier.

pkg_metaread-only

Package metadata in one call, cheapest tier: latest and resolved version, license, first/last publish dates, weekly downloads, deprecation flag, install script…

homework_checkread-only

Can this homework be done by an AI?

verify_businessread-only

KYB company verification and business registry verification before paying, onboarding or contracting a company (vendor due diligence).

web_searchread-only

Web search with page content: search the web and read the top pages in ONE call.

company_enrichread-only

Company profile from a domain or name in ONE call, for sales and research agents: what the company does, industry, services, service area, address, phones and …

company_fitread-only

Is this company worth contacting FOR YOU?

payment_checkread-only

Check an x402 endpoint before paying it: is this x402 seller safe to pay?

sanctions_checkread-only

Sanctions screening of a company name (OFAC, US, UK, EU, Canada), cheapest tier: is this company sanctioned?

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
1 warning
- !summarize and translate have nearly the same description (60% of their words are shared; the only difference: "summarize", "40k", "char" vs "translate", "between", "french"), so an AI may not know which to pick
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !1 tool answers with structured data but doesn't declare its shape (outputSchema): pkg_check. If those answers change shape, nothing can catch it; with a schema, every answer is checked.
note
✓
ConnectsConnected in 414 ms
pass
✓
Lists its toolsFound 15 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
- ✓pkg_check: Worked (1.7 s)
- ✓qc_contractor_check: Answered with an error, probably because of our sample input: Provide neq, licence or name.
- ✓summarize: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.03, "how": "This tool costs $0.03 USDC on Base or Solana (x402 v2). Either (a) call it over H…
- ✓translate: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.04, "how": "This tool costs $0.04 USDC on Base or Solana (x402 v2). Either (a) call it over H…
- ✓extract: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.02, "how": "This tool costs $0.02 USDC on Base or Solana (x402 v2). Either (a) call it over H…
- ✓extract_url: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.03, "how": "This tool costs $0.03 USDC on Base or Solana (x402 v2). Either (a) call it over H…
- ✓qc_licence: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.01, "how": "This tool costs $0.01 USDC on Base or Solana (x402 v2). Either (a) call it over H…
- ✓pkg_meta: Answered with an error, probably because of our sample input: { "error": "payment_required", "price_usd": 0.002, "how": "This tool costs $0.002 USDC on Base or Solana (x402 v2). Either (a) call it over…
- and 7 more
pass
✓
Bad inputs give a clean error
All good
- ✓pkg_check: Refused missing required input "name" with a clear error
- ✓pkg_check: Refused wrong type for "name" with a clear error
- ✓qc_contractor_check: Refused wrong type for "neq" with a clear error
- ✓summarize: Refused missing required input "text" with a clear error
- ✓summarize: Refused wrong type for "text" with a clear error
- ✓translate: Refused missing required input "text" with a clear error
- ✓translate: Refused wrong type for "text" with a clear error
- ✓extract: Refused missing required input "text" with a clear error
- and 17 more
pass
✓
Fast enough
All good
- ✓Connecting took 414 ms
- ✓Listing tools took 104 ms
- ✓Average tool answer: 170 ms
- ✓pkg_check: Slowest tool: pkg_check (1.7 s)
pass
✓
No secrets leakedChecked 39 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.

npx qamcp-cli https://tolca.tonbot.ca/mcp

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.

[![QAmcp score](https://qamcp.dev/s/ca-tonbot-tolca-tolca.svg)](https://qamcp.dev/s/ca-tonbot-tolca-tolca.html)

Score over time

9 Nov 202688

One test so far. New tests will show here.

Reviews

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

Is this your server? Get an alert the moment it breaks.

QAmcp Monitor tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. Free for 1 server, no card.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works