Cracked
Tool router for AI agents: discover, inspect and run 13,131 endpoints across 1,183 providers and 54,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 162 smart-run capabilities route a task to the healthiest live tool with automatic fallback. Agents can register their own workspace at POST https://cracked.ai/v1/agents/register ($1 trial credit, no human needed) and earn $5 of credit for every workspace that signs up through their referral link (GET https://cracked.ai/v1/referrals).
AgentCard object, but omits optional fields an agent may expect.
no-preferredTransport
/.well-known/agent.json, the
pre-0.3 location, rather than the current /.well-known/agent-card.json. Clients written
against A2A 1.0.0 will not find it.
An A2A client finds this agent by fetching the well-known path on the provider's own host. That is what makes an agent card different from every other agent artifact in this catalog: it is provider-published by construction — it cannot be derived, generated, or reconstructed on a provider's behalf.
https://cracked.ai/mcp
· transport streamable-http
· protocol mcp
https://cracked.ai/mcp/public
· transport streamable-http
· protocol mcp
https://cracked.ai/v1
· transport http
· protocol rest
https://cracked.ai/SKILL.md
· transport text
· protocol skill
Weather forecast weather-forecast
Current conditions plus daily forecast for coordinates. Use geocode first for a city name. 104 measured runs in the last 30 days across 1 candidate tools. Input fields: latitude, longitude, days, units.
weatherforecasttemperaturerainconditionsScrape page to text web-scrape
Fetch one URL and return its readable content (text or markdown) plus title and metadata. 99 measured runs in the last 30 days across 5 candidate tools. Input fields: url, max_chars.
scrapefetchreadurlpagemarkdownextractcrawlPyPI package pypi-package
PyPI package metadata: latest version, summary, license, requires-python, project URLs, release list. 80 measured runs in the last 30 days across 2 candidate tools. Input fields: name.
pypipythonpackagepipdependencyversionCompany enrichment company-enrich
Firmographics for a company by website domain: name, industry, size, location, description, socials. 79 measured runs in the last 30 days across 3 candidate tools. Input fields: domain.
companyenrichenrichmentfirmographicsdomainb2borganizationShopify store products shopify-store-products
Product catalog of any Shopify storefront by domain: title, variants, prices, images, availability. 74 measured runs in the last 30 days across 3 candidate tools. Input fields: store, limit.
shopifystoreproductscatalogpricesecommercecompetitorGitHub repository github-repo
Repository metadata: description, stars, forks, language, license, default branch, topics. 73 measured runs in the last 30 days across 2 candidate tools. Input fields: repo.
githubreporepositorystarsopen sourcecodeWeb search web-search
Search the web and get ranked results with titles, URLs and snippets. 43 measured runs in the last 30 days across 7 candidate tools. Input fields: query, limit.
searchgoogleserpwebresultsinternetLLM completion llm-chat
Generate text with a frontier or open model. Cheapest live model first. 39 measured runs in the last 30 days across 9 candidate tools. Input fields: prompt, system, max_tokens, json.
llmchatcompletiongptclaudegeminigenerate textpromptmodelTranslate text translate
Translate text between languages. 34 measured runs in the last 30 days across 4 candidate tools. Input fields: text, to, from.
translatetranslationlanguagelocalizeExtract keywords keyword-extract
Most important keywords and key phrases in a text, ranked (JSON array). 34 measured runs in the last 30 days across 5 candidate tools. Input fields: text, limit.
keywordsextractkey phrasestopicstagsnlpseoSolve a math problem math-solve
Step-by-step solution and final answer for a math problem (JSON). 34 measured runs in the last 30 days across 6 candidate tools. Input fields: problem.
mathsolveequationcalculatealgebracalculuswolframContent moderation moderation
Flag text for harassment, hate, sexual content, violence, self-harm and spam, with per-category scores (JSON). 34 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
moderationsafetytoxicityflagcontent policyabusespamSentiment analysis sentiment
Classify the sentiment of a text as positive, neutral or negative with a score and short rationale (JSON). 34 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
sentimentclassifypositivenegativereviewsnlpopinionSummarize text summarize-text
Concise summary of a passage of text, with a configurable length. 34 measured runs in the last 30 days across 5 candidate tools. Input fields: text, sentences.
summarizesummarytldrcondensetextabstractDetect language translate-detect
Identify the language of a text. Returns JSON with language name, ISO code and confidence. 34 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
languagedetectidentifytranslatelocaleiso codeUnit conversion unit-convert
Convert a value between units (length, mass, temperature, volume, speed, data, energy) with the result as JSON. 34 measured runs in the last 30 days across 6 candidate tools. Input fields: value, from, to.
unitsconvertconversionmetricimperialtemperaturemeasurementDocumentation search docs-search
Search developer documentation or one docs site for a question and get the most relevant pages with content. 33 measured runs in the last 30 days across 5 candidate tools. Input fields: query, site, limit.
docsdocumentationdeveloperapi referencesearchreadmePDF text extraction pdf-extract
Extract the text (markdown where possible) from a hosted PDF. 26 measured runs in the last 30 days across 5 candidate tools. Input fields: url.
pdfextracttextdocumentparsereadInstagram profile instagram-profile
Profile details for an Instagram account: followers, following, bio, verified, recent post count. 21 measured runs in the last 30 days across 3 candidate tools. Input fields: username.
instagramigprofilefollowersbioaccountJob search jobs-search
Job listings matching a title or keyword, optionally in a location. 19 measured runs in the last 30 days across 5 candidate tools. Input fields: query, location, limit.
jobsjobhiringcareersindeedlinkedin jobspositionsopenings2026-09-03 from https://cracked.ai/.well-known/agent.json,
HTTP 200. The body was saved verbatim and is the sole source for
everything on this page — no field is inferred.
View the captured card.
Providers change what they serve; if this card has moved or changed shape,
the provider profile carries the
current state as of the last build.
Work with this as data
Every agent card here is available over the APIs.io API and to AI agents over MCP. A2A Agent Cards is not yet its own endpoint on the v1 API. Reach it through catalog search and the tag graph, or the MCP server.