Cracked

Tool router for AI agents: discover, inspect and run 13,713 endpoints across 1,225 providers and 90,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 170 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).

Skills

• LLM completion
  Generate text with a frontier or open model. Cheapest live model first. 492 measured runs in the last 30 days across 9 candidate tools. Input fields: prompt, system, max_tokens, json.
  llmchatcompletiongptclaudegeminigenerate textpromptmodel
• Extract keywords
  Most important keywords and key phrases in a text, ranked (JSON array). 410 measured runs in the last 30 days across 5 candidate tools. Input fields: text, limit.
  keywordsextractkey phrasestopicstagsnlpseo
• Solve a math problem
  Step-by-step solution and final answer for a math problem (JSON). 410 measured runs in the last 30 days across 6 candidate tools. Input fields: problem.
  mathsolveequationcalculatealgebracalculuswolfram
• Content moderation
  Flag text for harassment, hate, sexual content, violence, self-harm and spam, with per-category scores (JSON). 410 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
  moderationsafetytoxicityflagcontent policyabusespam
• Sentiment analysis
  Classify the sentiment of a text as positive, neutral or negative with a score and short rationale (JSON). 410 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
  sentimentclassifypositivenegativereviewsnlpopinion
• Summarize text
  Concise summary of a passage of text, with a configurable length. 410 measured runs in the last 30 days across 5 candidate tools. Input fields: text, sentences.
  summarizesummarytldrcondensetextabstract
• Detect language
  Identify the language of a text. Returns JSON with language name, ISO code and confidence. 410 measured runs in the last 30 days across 5 candidate tools. Input fields: text.
  languagedetectidentifytranslatelocaleiso code
• Unit conversion
  Convert a value between units (length, mass, temperature, volume, speed, data, energy) with the result as JSON. 410 measured runs in the last 30 days across 6 candidate tools. Input fields: value, from, to.
  unitsconvertconversionmetricimperialtemperaturemeasurement
• Translate text
  Translate text between languages. 269 measured runs in the last 30 days across 4 candidate tools. Input fields: text, to, from.
  translatetranslationlanguagelocalize
• Voice clone speech
  Speak text in the voice of a short reference audio clip (zero-shot voice cloning). 60 measured runs in the last 30 days across 3 candidate tools. Input fields: text, audio_url.
  voiceclonettsspeechreference audiotext to speech
• Weather forecast
  Current conditions plus daily forecast for coordinates. Use geocode first for a city name. 49 measured runs in the last 30 days across 1 candidate tools. Input fields: latitude, longitude, days, units.
  weatherforecasttemperaturerainconditions
• Remove image background
  Cut out the subject of an image and return a transparent PNG. 40 measured runs in the last 30 days across 3 candidate tools. Input fields: image_url.
  backgroundremove backgroundcutouttransparentpngimageproduct photo
• Generate music
  Create a music track from a text description. Asynchronous on most models: send wait=false and poll. 40 measured runs in the last 30 days across 3 candidate tools. Input fields: prompt, instrumental.
  musicgeneratesongaudiosunosoundtrackjingle
• Video captions
  Timestamped captions (subtitles) for a hosted video or audio file, or a YouTube video. 21 measured runs in the last 30 days across 3 candidate tools. Input fields: url, language.
  captionssubtitlessrtvideotranscribetimestampsyoutube
• Image caption
  Describe what is in an image in natural language. 20 measured runs in the last 30 days across 2 candidate tools. Input fields: image_url.
  imagecaptiondescribevisionalt textphoto
• Upscale image
  Increase an image's resolution 2x to 4x with an AI upscaler. 20 measured runs in the last 30 days across 2 candidate tools. Input fields: image_url, scale.
  upscaleenhanceresolutionimageenlargesuper resolution
• Generate video
  Create a short video clip from a text prompt. Asynchronous: send wait=false and poll the run. 20 measured runs in the last 30 days across 3 candidate tools. Input fields: prompt, aspect_ratio.
  videogenerategenerationclipveoklingtext to video
• Web search
  Search the web and get ranked results with titles, URLs and snippets. 10 measured runs in the last 30 days across 7 candidate tools. Input fields: query, limit.
  searchgoogleserpwebresultsinternet
• Documentation search
  Search developer documentation or one docs site for a question and get the most relevant pages with content. 9 measured runs in the last 30 days across 5 candidate tools. Input fields: query, site, limit.
  docsdocumentationdeveloperapi referencesearchreadme
• Google Shopping
  Product offers for a query across merchants: title, price, seller, rating, product URL. 7 measured runs in the last 30 days across 2 candidate tools. Input fields: query, limit.
  google shoppingshoppingpricesproductsoffersprice comparison
• Agent profile
  Per-key routing defaults: preferred and blocked providers honoured by every smart run and waterfall, default max cost per run and default max latency, free-form tags and notes. Explicit prefer, exclude, max_cost_usd and maxLatencyMs on a request always win.
  profileroutingbudgetpreferences
• Agent memory
  Key-scoped store and recall: one JSON value per name (64 KB), 200 names per key, listed with sizes. For cursors, run ids and preferences between sessions; no search or embeddings.
  memorystatekey-value
• Recipes
  Named input templates over a capability or a tool with saved run options (prefer, exclude, max_cost_usd, cache, tag). Running a recipe merges the call's input over the template and bills like any run; the recipe counts its runs.
  recipestemplatesautomation

How to call

https://cracked.ai/mcp

Listed in

Directories this entry was found in.