Toolbox
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.
| Author | com.allthepossibles |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2235 ms |
| Last measured | 2026-10-24 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"Toolbox": {
"url": "https://toolbox.allthepossibles.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (14)
check_tellsread-onlyCheck 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, hidden Unicode) and return a score, each tell with its position, and a cleaned copy. Run it on anything you are about to publish on a human's behalf.
Parameters:
text(required) — string — The text to check. Free tier: 3,000 chars.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
manifest_costread-onlyEstimate 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 descriptions, base64 blobs and echoed schemas. Pass a live Streamable HTTP endpoint or a tools array.
Parameters:
url— string — Streamable HTTP MCP endpointtools— array — Tool definitions, if the server is not reachable over HTTP
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
lint_agent_mdread-onlyLint 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, leftover TODO markers, hidden characters, empty headings.
Parameters:
text(required) — string — File contentsfilename— string — e.g. CLAUDE.md or MEMORY.md; changes the severity of the line cap
Hints: read-only yes · destructive no · idempotent not declared · open-world no
mcp_install_snippetsread-onlyGenerate install snippets for an MCP endpoint (Claude Code, Claude Desktop, Cursor, Codex, VS Code, curl) and probe the endpoint once to confirm it answers initialize and tools/list.
Parameters:
url(required) — stringname— string — Server name to use in configsprobe— booleanheaderName— stringheaderValue— string
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
check_ai_crawlersread-onlyRead a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or partially blocked; check for llms.txt and draft one from the site's metadata and sitemap.
Parameters:
url(required) — string — Any URL on the site
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
check_headersread-onlyFetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cache-Control, cookie Secure/HttpOnly/SameSite flags, and server version leaks. Returns a grade, a score and the exact header to add for each gap.
Parameters:
url(required) — string — The page to fetch
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
check_page_metaread-onlyFetch a URL and report what crawlers and link unfurlers see: title and meta description with lengths, canonical, lang, viewport, robots meta, h1s, Open Graph and Twitter card tags, favicon, JSON-LD types, the resulting preview card, and findings for anything missing or too long.
Parameters:
url(required) — string — The page to fetch
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
json_to_schemaread-onlyTurn a JSON sample (or an array of samples of the same shape) into a JSON Schema draft 2020-12 and a TypeScript type. Infers required vs optional keys across samples, nullable fields, integer vs number, date/email/uri/uuid formats, and small enums. Use it to draft an MCP tool inputSchema from an example payload.
Parameters:
json(required) — string — The JSON text. Free tier: 20,000 chars.name— string — Type name, default Root
Hints: read-only yes · destructive no · idempotent not declared · open-world no
explain_cronread-onlyExplain 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 handle differently (nicknames, six fields, day-of-month plus day-of-week, sub-5-minute intervals, day 31).
Parameters:
expression(required) — string — e.g. 0 */6 * * 1-5from— string — ISO date to compute next runs from, default nowcount— integer — How many next runs to list, 1 to 20, default 5
Hints: read-only yes · destructive no · idempotent not declared · open-world no
scrub_envread-onlyScrub 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). Returns the example, the secrets found (AWS, GitHub, Stripe, Slack, Google, OpenAI, Anthropic, Resend, SendGrid, Twilio, Cloudflare, JWTs, private keys, database URLs, high-entropy strings) by key, kind and line with only the first 4 characters and the length, and findings for duplicate keys, non-UPPER_SNAKE names, unbalanced quotes, export prefixes and trailing spaces.
Parameters:
text(required) — string — The .env file contents. Free tier: 20,000 chars.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
trace_redirectsread-onlyTrace a URL's redirect chain hop by hop (up to 10 hops, 8 s each) with status, location, timing and scheme per hop. Flags chains over two redirects, loops, HTTPS-to-HTTP downgrades, 302s used for www or https canonicalisation, dropped paths or query strings, cross-domain moves, meta-refresh or JS redirects on a 200, and a final page that is not 200.
Parameters:
url(required) — string — URL to trace, e.g. http://example.com
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
check_sitemapread-onlyCheck 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 per file and per host, summarises lastmod, and fetches a sample of URLs (HEAD, then GET) to count the ones that are not 200. Flags a missing sitemap, no robots.txt entry, over 50,000 URLs, other hosts, http URLs on https sites and missing lastmod.
Parameters:
url(required) — string — Any URL on the sitesample— integer — How many sitemap URLs to fetch, default 10, max 25 on free and 100 on Pro
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
decode_jwtread-onlyDecode a JWT's header and payload without verifying the signature (it never takes a secret). Returns the claims with iat, nbf and exp as ISO times, a plain-text expiresIn, issuer, subject and audience, and findings: alg none, HS* with a URL-like kid, missing or distant exp, expired, nbf or iat in the future, payload over 4 KB, sensitive field names, and jku or x5u pointing off-site.
Parameters:
token(required) — string — The JWT, three dot-separated parts. A leading Bearer is ignored.
Hints: read-only yes · destructive no · idempotent not declared · open-world no
lint_mcp_toolsread-onlyLint 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-identical descriptions, instruction-like text in a description, arguments with no description, required arguments missing from properties, destructive-sounding tools with no destructiveHint, and unbounded free-text arguments on them. Pass a live Streamable HTTP endpoint or a tools array.
Parameters:
url— string — Streamable HTTP MCP endpointtools— array — Tool definitions, if the server is not reachable over HTTP
Hints: read-only yes · destructive no · idempotent not declared · open-world yes
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.