{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_86vr8v5fw73w","handle":"toolbox","url":"https://wellknown.network/agents/toolbox","links":{"self":"https://wellknown.network/agents/toolbox/record.json","html":"https://wellknown.network/agents/toolbox","markdown":"https://wellknown.network/agents/toolbox/record.md","api":"https://wellknown.network/api/v1/agents/toolbox","status":"https://wellknown.network/api/v1/agents/toolbox/status","claim":"https://wellknown.network/agents/toolbox/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/toolbox/claim.json","badge":"https://wellknown.network/agents/toolbox/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/toolbox/history","tools":"https://wellknown.network/api/v1/agents/toolbox/tools"},"ard":{"identifier":"urn:air:toolbox.allthepossibles.com:server:toolbox","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Toolbox","summary":"Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.","description":"Small tools for agent builders: AI-writing tells, tools/list token cost, CLAUDE.md lint, and more.","publisher":{"name":"com.allthepossibles","url":null},"homepage":"https://toolbox.allthepossibles.com","repository":null,"version":"1.0.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://toolbox.allthepossibles.com/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-10-19T16:30:12.320932Z","publishedAt":"2026-10-19T16:30:12.320932Z","registryName":"com.allthepossibles/toolbox"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"commerce.pricing","name":"Pricing & Quotes","confidence":1,"provenance":"derived"},{"slug":"content.writing","name":"Writing & Editing","confidence":0.911,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.583,"provenance":"derived"},{"slug":"security.identity","name":"Identity & Access","confidence":0.569,"provenance":"derived"},{"slug":"infra.cloud","name":"Cloud Platforms","confidence":0.554,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.525,"provenance":"derived"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":0.51,"provenance":"derived"}],"categories":["commerce","content","data","dev","infra","security"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 4h ago.","lastOkAt":"2026-10-27T06:24:31.762Z","lastProbedAt":"2026-10-27T06:24:31.762Z","statusComputedAt":"2026-10-27T06:26:18.659Z","reliability30d":{"probes":20,"successRate":1,"p50Ms":31,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":20,"ok":20,"authBoundaryOk":0,"serviceOk":20,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-27T06:24:31.762Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":26,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-26T23:23:44.180Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":29,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-26T16:28:50.364Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":26,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-26T09:33:30.985Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":42,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-26T02:24:43.867Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":20,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-25T19:27:50.705Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":29,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-25T11:30:12.623Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":45,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-25T04:26:21.586Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":29,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T21:26:44.095Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":19,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T14:22:13.536Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":42,"error":null,"detail":{"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"toolCount":14,"toolsHash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","serverName":"toolbox","capabilities":["tools"],"serverVersion":"0.1.0","protocolVersion":"2025-06-18"}}],"tools":[{"name":"check_tells","description":"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, hidde"},{"name":"manifest_cost","description":"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 descripti"},{"name":"lint_agent_md","description":"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, le"},{"name":"mcp_install_snippets","description":"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 init"},{"name":"check_ai_crawlers","description":"Read a site's robots.txt and report which AI crawlers (GPTBot, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider and more) are allowed, blocked or pa"},{"name":"check_headers","description":"Fetch a URL once and grade its response headers: HSTS, Content-Security-Policy, X-Content-Type-Options, frame control, Referrer-Policy, Permissions-Policy, Cach"},{"name":"check_page_meta","description":"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 an"},{"name":"json_to_schema","description":"Turn 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 sa"},{"name":"explain_cron","description":"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 handle"},{"name":"scrub_env","description":"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). Retur"},{"name":"trace_redirects","description":"Trace 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, HTTP"},{"name":"check_sitemap","description":"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 pe"},{"name":"decode_jwt","description":"Decode 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"},{"name":"lint_mcp_tools","description":"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-id"}],"package":null,"toolSurface":{"id":"ts_gz365psrr7qw","endpointId":"ep_3xca7hnnvp42","hash":"e6407a29bd3a586f438d945df1c45a9d9e34788b3b60a1b9938a1caebe627dc8","toolCount":14,"serverName":"toolbox","serverVersion":"0.1.0","protocolVersion":"2025-06-18","firstSeenAt":"2026-10-21T23:28:53.231Z","lastSeenAt":"2026-10-27T06:24:31.772Z","observations":19,"toolNames":["check_tells","manifest_cost","lint_agent_md","mcp_install_snippets","check_ai_crawlers","check_headers","check_page_meta","json_to_schema","explain_cron","scrub_env","trace_redirects","check_sitemap","decode_jwt","lint_mcp_tools"],"distinctSurfaces":2},"endpointFacts":[{"id":"ep_3xca7hnnvp42","url":"https://toolbox.allthepossibles.com/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-25T19:27:50.715Z","auth":{"observedAt":"2026-10-25T19:27:50.797Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-25T19:27:50.818Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"allthepossibles.com","issuer":{"commonName":"WE1","organization":"Google Trust Services"},"validFrom":"2026-10-19T15:22:55.000Z","validTo":"2027-01-17T16:22:52.000Z","daysToExpiry":82,"sanCount":3,"fingerprint256":"96:D0:A1:A9:98:FB:C6:B0:FF:A9:A9:7E:9D:BF:B8:E0:98:25:99:D2:76:42:50:EC:22:55:6E:B2:C5:77:C4:83"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"com.allthepossibles/toolbox","url":"https://registry.modelcontextprotocol.io/v0/servers/com.allthepossibles%2Ftoolbox","firstSeenAt":"2026-10-21T12:20:41.242Z","fetchedAt":"2026-10-25T00:22:20.912Z","normalizedAt":"2026-10-25T00:22:20.912Z"}]},"firstSeenAt":"2026-10-21T12:20:41.242Z","updatedAt":"2026-10-27T06:27:11.916Z"}