io.github.jeffreyturov-dev/adaga-solutions-toolbox

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services.

1 of 13 tools are described as changing something (creating, editing, deleting, sending or running). For 3 the reading was uncertain, so no mark is shown.

• local_presence_auditreads or searches

  “Deep audit of ONE local business's online presence in a single run: Google Business Profile data (rating, review count, category, contact), recent reviews with urgency classification and owner-respon…”

  6 inputs

  • querystring“Business name + city used to find its Google Maps profile (e.g.”
  • websiteUrlstring“Full URL of the business website (e.g.”
  • maxReviewsinteger“Number of most recent Google reviews to scrape and classify (urgency detection, owner-response check).”
  • languagestring“Google Maps interface language code (fr, en, de...).”
  • dryRunboolean“When true, the actor runs fully but skips all pay-per-event charges.”
  • proxyConfigurationobject“Apify proxy settings.”
• google_maps_scraperreads or searches

  “Extract local business data from Google Maps IN BULK: names, addresses, phones, ratings, review counts, websites, GPS coordinates — up to 100 businesses per call (refine the query for narrower result…”

  7 inputs

  • searchQuerystring“What to search on Google Maps (e.g., 'restaurants Paris', 'plumbers London', 'hotels New York')”
  • queriesarray“Array of search queries to scrape.”
  • maxResultsinteger“Maximum number of businesses to extract per query”
  • languagestring“Language code for Google Maps results (e.g., 'fr', 'en', 'de', 'es')”
  • includeReviewsboolean“Whether to extract user reviews for each business”
  • maxReviewsinteger“Maximum number of reviews to extract per business”
  • proxyConfigurationobject“Proxy settings.”
• tiktok_scraperreads or searches

  “Scrape TikTok profiles and videos: follower counts, likes, video metadata and stats.”

  3 inputs, 1 required

  • profilesarrayrequired“List of TikTok usernames or profile URLs to scrape (e.g., ['mrbeast', 'https://www.tiktok.com/@charlidamelio'])”
  • hashtagsarray“List of hashtags to scrape trending videos from (without #)”
  • maxVideosPerProfileinteger“Maximum number of videos to extract per profile”
• instagram_scraperreads or searches

  “Scrape Instagram profiles and hashtag posts: followers, posts, engagement metrics.”

  1 input, 1 required

  • profilesarrayrequired“List of Instagram usernames to scrape (without @).”
• youtube_scraperreads or searches

  “Scrape YouTube videos and channels: views, subscribers, metadata, descriptions.”

  4 inputs

  • videoUrlsarray“YouTube video URLs or IDs to scrape.”
  • channelUrlsarray“YouTube channel URLs to scrape.”
  • searchQueriesarray“Search YouTube for videos matching these queries.”
  • maxResultsinteger“Maximum number of results per search query (1-50)”
• linkedin_profile_scraperreads or searches

  “Extract public LinkedIn profile data with this scraper: name, headline, experience, company.”

  3 inputs, 1 required

  • profileUrlsarrayrequired“List of LinkedIn profile URLs to scrape (e.g., ['https://www.linkedin.com/in/williamhgates/'])”
  • includeSkillsboolean“Whether to extract the skills section”
  • includeExperienceboolean“Whether to extract work experience details”
• rag_web_browserreads or searches

  “Fetch web pages and convert them into clean LLM-ready text for RAG pipelines.”

  5 inputs

  • querystring“Google search query.”
  • urlsarray“Direct page URLs to extract content from (instead of searching).”
  • maxResultsinteger“Maximum number of search results / pages to process”
  • outputFormatstring“Content format: markdown (best for LLM/RAG) or plain text”
  • langstring“Language code for search results (e.g.”
• api_breaking_change_radarreads or searches

  “Monitor public APIs and detect breaking changes by diffing OpenAPI specs and classifying changelogs — a radar for the APIs you depend on.”

  4 inputs, 1 required

  • apisarrayrequired“List of APIs to watch.”
  • webhookUrlstring“POST endpoint called at the end of each run with a JSON summary (counts by class + top critical changes).”
  • dryRunboolean“When true, the actor performs the full detection but does NOT charge any pay-per-event fee.”
  • maxApisinteger“Safety cap on the number of APIs processed in one run.”
• review_radarreads or searches

  “Monitor Google Maps reviews and detect only NEW ones since previous runs (stateful tracking per business), with Bayesian urgency classification and optional Slack alerts — your reputation radar.”

  8 inputs

  • placeUrlsarray“Google Maps place URLs (/maps/place/...) to monitor”
  • querystring“Google Maps search, e.g.”
  • maxPlacesinteger“How many businesses to monitor (from placeUrls or the search query)”
  • maxReviewsPerPlaceinteger“How many recent reviews to scrape per business”
  • alertThresholdinteger“New reviews with this rating or lower trigger a Slack alert”
  • dryRunboolean“Testing mode: skips Slack alerts, state writes, and billing events”
  • slackConnectorstring“MCP connector to your Slack workspace.”
  • proxyConfigurationobject“A residential proxy is strongly recommended — Google Maps blocks datacenter IPs.”
• review_pitch_generatorgenerates contentdescribed as changing data

  “Generate pre-sales reports from a business's worst Google Maps reviews: HTML report plus ready-to-send pitch.”

  15 inputs

  • placeUrlsarray“Google Maps place URLs (/maps/place/...) of the prospects to analyze”
  • querystring“Google Maps search, e.g.”
  • maxPlacesinteger“How many prospects to analyze”
  • maxReviewsPerPlaceinteger“How many recent reviews to scan per business when looking for the worst”
  • worstThresholdinteger“Reviews at or below this rating are included in the pitch report”
  • modestring“generate = scrape + pitch + delivery.”
  • telemetryEndpointstring“Base URL of our tracking receiver (e.g.”
  • verticalstring“Sector template for pitch/report: chr (hotels/restaurants), immobilier, sante, artisanat”
  • emailMapobject“Mapping place name or Maps URL -> recipient email for outbound delivery.”
  • smtpUserstring“Gmail address used to send reports (requires an app password).”
  • smtpPasswordstring“Gmail app password for the SMTP user.”
  • sendApprovalboolean“Explicit approval gate: without it, NO email is ever sent (reports are generated only)”
  • maxEmailsPerRuninteger“Rate limit: maximum reports emailed in one run (plus 20s inter-send delay and a 20/day global cap)”
  • dryRunboolean“Testing mode: skips report publishing and billing events”
  • proxyConfigurationobject“A residential proxy is strongly recommended — Google Maps blocks datacenter IPs.”
• france_fuel_pricesreads or searches

  “Get live fuel prices for about 10,000 gas stations across France (official open data, Hermès Revenu API).”

  2 inputs

  • departementstring“Filtrer par code département (ex: '75' pour Paris, '69' pour Lyon).”
  • carburantstring“Filtrer par type de carburant”
• hotel_rate_monitoringreads or searches

  “Monitor hotel rates across booking sources for revenue management.”

  Takes no inputs.

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.