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

SoonYour score can change any day. QAmcp Monitor tests your server every hour and emails you when it breaks.See what Monitor does →

Directory / Toolbox

Toolbox

Q: Is Toolbox MCP server safe?

QAmcp's test on 30 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. All 14 of its tools are labeled read-only. Overall it scored 88/100 on 30 Oct 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 toolbox.allthepossibles.com · https://toolbox.allthepossibles.com/mcp

Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.

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

Visit website

88 /100

PASS · WITH NOTES

11 of 11 checks · 30 Oct 2026

Is Toolbox MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
All 14 of its tools are labeled read-only.
Overall it scored 88/100 on 30 Oct 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

14 tools, in the server's own words.

check_tellsread-only

Check text for AI-writing tells (em-dashes, 'not just X but Y', rule-of-three lists, stock vocabulary like delve or seamlessly, hedge words, smart quotes, hidd…

manifest_costread-only

Estimate what an MCP server's tools/list costs in tokens on every session start, per tool, with the three most expensive tools and flags for oversized descript…

lint_agent_mdread-only

Lint a CLAUDE.md, AGENTS.md or MEMORY.md: line count against Claude Code's 200-line memory index cap, estimated tokens, duplicate lines, contradicting rules, l…

mcp_install_snippetsread-only

Generate install snippets for an MCP endpoint (Claude Code, Claude Desktop, Cursor, Codex, VS Code, curl) and probe the endpoint once to confirm it answers ini…

check_ai_crawlersread-only

Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or p…

check_headersread-only

Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cac…

check_page_metaread-only

Fetch a URL and report what crawlers and link unfurlers see: title and meta description with lengths, canonical, lang, viewport, robots meta, h1s, Open Graph a…

json_to_schemaread-only

Turn a JSON sample (or an array of samples of the same shape) into a JSON Schema draft 2020-12 and a TypeScript type.

explain_cronread-only

Explain a five-field cron expression in plain English, list the next runs in UTC, and warn about the cases Cloudflare Workers, GitHub Actions and crontab handl…

scrub_envread-only

Scrub a .env file into a safe .env.example: every value is blanked or replaced with a placeholder that keeps its shape (postgres://USER:PASSWORD@HOST/DB).

trace_redirectsread-only

Trace a URL's redirect chain hop by hop (up to 10 hops, 8 s each) with status, location, timing and scheme per hop.

check_sitemapread-only

Check a site's sitemaps: discovers them from robots.txt, /sitemap.xml and /sitemap_index.xml, reads index files one level deep (20 children max), counts URLs p…

decode_jwtread-only

Decode a JWT's header and payload without verifying the signature (it never takes a secret).

lint_mcp_toolsread-only

Lint the tools an MCP server lists, from the model's side of the wire: names that break Claude's ^[a-zA-Z0-9_-]{1,64}$ rule, duplicate names, missing or near-i…

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 (2025-06-18). It works today, but it isn't on the July 2026 version (2026-07-28) yet.
note
!
Every tool is described
1 warning
- !mcp_install_snippets: Inputs with no description: url, headerName, headerValue, probe
note
!
Follows MCP best practices (not scored yet)
1 tip (not scored)
- !lint_agent_md: Labeled read-only, but its "filename" input is a file path with no pattern, length limit or fixed choices. Make sure the server first resolves the real path (following links and encoded dots like %2e%2e), then refuses anything outside its f
note
✓
ConnectsConnected in 178 ms
pass
✓
Lists its toolsFound 14 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Tools work with good inputs
All good
- ✓check_tells: Worked (291 ms)
- ✓manifest_cost: Answered with an error, probably because of our sample input: provide `url` (a Streamable HTTP MCP endpoint) or `tools` (an array of tool definitions)
- ✓lint_agent_md: Worked (235 ms)
- ✓mcp_install_snippets: Worked (223 ms)
- ✓check_ai_crawlers: Worked (205 ms)
- ✓check_headers: Worked (192 ms)
- ✓check_page_meta: Worked (228 ms)
- ✓json_to_schema: Answered with an error, probably because of our sample input: provide valid JSON in `json`: Unexpected token 'e', "test" is not valid JSON
- and 6 more
pass
✓
Bad inputs give a clean error
All good
- ✓check_tells: Refused missing required input "text" with a clear error
- ✓check_tells: Refused wrong type for "text" with a clear error
- ✓manifest_cost: Refused wrong type for "url" with a clear error
- ✓lint_agent_md: Refused missing required input "text" with a clear error
- ✓lint_agent_md: Refused wrong type for "text" with a clear error
- ✓mcp_install_snippets: Refused missing required input "url" with a clear error
- ✓mcp_install_snippets: Refused wrong type for "url" with a clear error
- ✓check_ai_crawlers: Refused missing required input "url" with a clear error
- and 18 more
pass
✓
Fast enough
All good
- ✓Connecting took 178 ms
- ✓Listing tools took 14 ms
- ✓Average tool answer: 183 ms
- ✓check_tells: Slowest tool: check_tells (291 ms)
pass
✓
No secrets leakedChecked 62 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://toolbox.allthepossibles.com/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/com-allthepossibles-toolbox.svg)](https://qamcp.dev/s/com-allthepossibles-toolbox.html)

Score over time

30 Oct 202688

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Toolbox, 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 (coming soon) tests it every hour and emails you when it goes down, the score drops, a tool changes or a secret leaks. You'll also be able to claim this page and get a verified owner mark. Founding price: $19/month for life for the first 50 teams.

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