"Sauce Labs" matching MCP tools:

• estimate_media_jobA

  Odile LabsA

  Price an Odile Formats job in credits before anything is uploaded or charged; use it to tell the customer the cost and get their approval before unlock_job. Needs no sign-in and changes nothing. Photos are priced exactly. Reel, Feed and Square video outputs cost exactly 1 credit each; YouTube 16:9 costs 1 or 2 because the length is only known once the file is read. Returns { minimum_credits, maximum_credits, final_price_known, charge_now: 0, why }. An unknown preset or a photo count out of range returns an error naming the valid values (get_catalog lists them).

  ConnectorOAuth

• get_demo_health_recordA

  FinchNode Synthetic Health RecordsA

  Get any mix of demographics, medications, conditions, labs, vitals, allergies, immunizations, encounters in one call — prefer this over several single-category tools. Builds a record view using the authenticated API normalized data shape (schemaVersion 2). Fictional patients only; pick one with scenario. Consent and sync are simulated, with no usable change cursor. Empty categories describe the fixture only.

  ConnectorNo auth

• create_media_jobA

  Odile LabsA

  Queue an Odile Formats job from sources uploaded with prepare_upload's helper. Costs nothing: credits are only spent by unlock_job, after the customer approves. One set of uploads makes exactly one job: calling it again with the same sources returns the existing job (replayed: true) whatever outputs, fit or trim are passed, so to render different outputs, upload again with prepare_upload. Needs a signed-in connection with write access. Returns at once with the job (same shape as get_job) plus replayed and next; poll get_job until state is ready.

  ConnectorOAuth

• research_keyword_volumeA

  tracetify-mcpA

  Google Ads (Keyword Planner) monthly search volume, CPC, competition, 12-month trend and keyword difficulty (0–100, DataForSEO Labs) for up to 10 keywords in one call. Use when the user asks how often something is searched or how hard it is to rank, or to size a keyword before writing a page. Omit location_code for worldwide volume (difficulty is then computed for the US), or pass a market code for one country. Costs credits; the same keyword set re-queried within a week is free.

  ConnectorNo auth

• get_jobA

  Odile LabsA

  One Odile Formats job by id, or the ten most recent when no id is given. Use it to poll a job after create_media_job (every 10-20 seconds, up to 10 minutes) until state is ready or failed; if it is still rendering after that, tell the customer and check again later (nothing is charged until unlock_job). Needs a signed-in connection and changes nothing. Returns one job { job_id, kind, state (queued | rendering | ready | failed), error, unlocked, credits_cost, credits_cost_known, credits_spent, outputs[{name, preset, ready, bytes, duration}], created_at, updated_at }, or { jobs[] } of the same shape. credits_cost is final only once credits_cost_known is true. An id that is not on this account returns 'No such job'. It reports status only: the files come from get_downloads after unlock_job, and a price before uploading comes from estimate_media_job.

  ConnectorOAuth

• validate_stlA

  HardCopy LabsA

  Check whether a 3D model can be printed, before ordering. A text validation quote is NOT approval to order. Call preview_print_order next, show its exact model images/options/price to the buyer, then obtain confirmation. Use this when the user has an STL file (base64-encoded) and wants to know if it is printable, or as a pre-check before submit_print_job. Returns printability (watertight/manifold status), dimensions, which printers it fits on, and the total for each material: what submit_print_job will charge for this file, shipping included. If the user is designing an object in this conversation, generate the STL, then call this to confirm it can be manufactured. Pass quantity (default 1) when the user wants several copies, so the totals cover all of them. For multiple parts, pass the WHOLE order in parts with each material/color/quantity. Never add separate quotes: totals already include shipping and handling once. To keep payloads small, validate each STL first and reuse its model_id (24 hours). PLA and PETG are the only materials offered.

  ConnectorNo auth

• submit_print_jobA

  HardCopy LabsA

  Create an order ONLY AFTER preview_print_order, image display and buyer confirmation. First present every preview image (or the viewer fallback), dimensions, material/color, quantity and quote. Obtain explicit buyer confirmation for that preview version. Then send preview_id, preview_version, buyer_confirmed=true, job_name and shipping details ONLY; omit model/options fields. Any relevant change needs a new preview. Legacy model inputs without a preview return a preview and NEVER create an order. Set geometry, material, color, quantities and operator notes in preview_print_order. OpenSCAD is preferred for designs made in conversation; uploaded STL and cached model IDs are also supported there. One preview covers the whole multi-part order. Confirm the shipping address with the buyer. ship_to requires their full name and US address; contact_email is used for updates. This returns a job ID and total, plus a payment link when payment is required. The buyer pays in their own browser.

  ConnectorNo auth

• reorder_print_jobA

  HardCopy LabsA

  A REORDER ALSO REQUIRES A NEW VISUAL PREVIEW AND BUYER CONFIRMATION. First call preview_print_order with reorder_of and any desired changes, show every image/options/price to the buyer, and obtain confirmation. Then call this with preview_id, preview_version and buyer_confirmed=true, without option overrides. Without a preview this returns a preview only; it never creates an order. In preview_print_order, quantity means complete sets for multi-part reorders; material/color overrides apply to every part. Omit overrides to preserve choices. Prices are recalculated. The previous order's geometry is reused without requesting a new upload. Shipping/contact details are never copied from the previous order; confirm the new address with the buyer. Orders cancelled by HardCopy Labs or still awaiting payment cannot be reordered. Returns a new job ID, total and payment link when payment is required, only after the new preview is confirmed.

  ConnectorNo auth

• get_federal_grantsA

  KeyVexA

  Returns federal GRANTS and cooperative agreements from USAspending. Distinct universe from get_federal_contracts — recipients here are universities, non-profits, state and local agencies, research labs, healthcare institutions, public-private partnerships. ⚠ award_amount and total_outlays are NULLABLE. USAspending omits Total Outlays from the search response for most grants, and this tool reports that as null rather than as $0 — a 0 means the source really said zero. Null-check before doing arithmetic. Null values never satisfy min_amount and sort last. Award type codes covered: 02 (Block Grant), 03 (Formula Grant), 04 (Project Grant — most common), 05 (Cooperative Agreement). Killer query patterns: - All NIH R01 grants this quarter: cfda_number='93.847' + since=... - State and local infrastructure funding: awarding_agency='Department of Transportation' + min_amount=1000000 - Recipient-specific grant history: recipient_name='Stanford' - Recipient by federal UEI: recipient_uei='ABC123XYZ' (most precise) Source: api.usaspending.gov — official Treasury federal-spending data. Awards covering both COVID/IIJA emergency-funding codes and routine appropriations. Pure-publisher posture: raw award data, no derived rankings or performance scores. COVERAGE — live passthrough (source:'live'): each call queries USAspending's API over the full dataset (2007-10 onward), with recipient/CFDA/min-amount/date filters applied server-side. The response's `total_count` is USAspending's authoritative grant count for your filtered query — USE IT for volume answers (the `results` array is just the requested page). `total_count` is omitted — and coverage_warning says why — when USAspending cannot count the answer: a recipient_uei that is also the PARENT of other recipients (USAspending cannot filter to one UEI's own grants), recipient_name combined with recipient_uei, or a start_date window (sort_by start_date with since/until). Then has_more is true whenever the search stopped before the end. Note: live cfda_number matching is against the award's FULL assistance-listings array (awards can carry several CFDAs); the cached fallback matches the primary listing only. On USAspending outage the tool falls back to a recent cached window (source:'cache' + coverage_warning) — don't infer volume there.

  ConnectorNo auth

• get_region_signalA

  Horizon AI IntelligenceA

  The current AI signal for a region (china, korea, japan, or eu) — recent, relevance-scored items on that region's models, labs, and analysis, ranked by momentum. Includes local-language press translated into English. The canonical regional tool; get_china_signal is a preset of this with region "china". Returns titles, sources, and links.

  ConnectorNo auth

• about_aetumiA

  aetumiA

  Return what AETumi is, what the platform does and its canonical links (site, docs, catalog, Labs). Platform facts only — it returns no assets, no experiences and no prices. For those use search_3d_web_assets, find_experiences or get_pricing. Read-only, no authentication, no side effects; returns public metadata.

  ConnectorNo auth

• get_demo_labsA

  FinchNode Synthetic Health RecordsA

  Use this to get only the lab results (labs) of baseline-adult, one of FinchNode's 12 synthetic scenarios from Northstar Health System (Synthetic) and Quillhaven Medical Group (Synthetic): Laboratory observations and reports, normalized from FHIR R4 Observation, DiagnosticReport. No account or API key. To get lab results together with other categories, call get_demo_health_record once instead of calling several of these tools.

  ConnectorNo auth

• prepare_uploadA

  Odile LabsA

  Step one of an Odile Formats job: returns a 30-minute upload token and the helper command. Run the helper in a shell on the customer's machine: file bytes go straight to Odile and never enter this conversation. The helper prints the source keys to pass to create_media_job. Needs a signed-in connection with write access; nothing is charged. Returns { kind, upload_token, expires_at, helper_url, run[], accepts, part_size, note }. One video OR up to ten photos per job. Each call mints a new token; earlier tokens stay valid until their own expiry, so call it again only when a token has expired or for a new job. To price a job first use estimate_media_job; for the file limits use get_catalog.

  ConnectorOAuth

• get_graph_nodeA

  weReciA

  Everything directly connected to one node, grouped by relationship: an entry's author/owner/source/ingredients/appliances/tools, an author's works, an ingredient's recipes, a user's collection. Exact and complete (unlike semantic search). Node ids are '<type>:<key>' — e.g. 'entry:<recipe uuid>' (prefix a search_recipes hit id with 'entry:'), 'ingredient:brown-sugar', 'author:mother-in-law', 'appliance:oven', 'user:<email>'. User-supplied metadata is traversable too: 'tag:<slug>' (a shared free-form label) and 'property:<key>:<value>' (a shared key=value, e.g. 'property:region:alaska') — every entry carrying that tag/value links to the same node. Recipes with named sub-preparations carry 'component:<entry uuid>:<slug>' nodes (HAS_COMPONENT from the entry; the component links to its own ingredients/steps) — e.g. "what else uses this sauce?" is one hop.

  ConnectorOAuth

• get_agent_opportunitiesA

  TensorFeedA

  Get TensorFeed's daily scan of new repositories across the AI agent ecosystem (Anthropic, OpenAI, Microsoft, ModelContextProtocol, HuggingFace, LangChain, frontier labs) plus recent MCP/x402/skills keyword sweeps. Each opportunity includes the GitHub repo path, description, stars, last update, the source signal, and a composite score (signal weight × log10(stars+1) × recency decay). Refreshed daily at 13:30 UTC. Useful for surfacing distribution targets, integration ideas, or just a daily digest of what's launching across the agent space. License: GitHub data via the public Search API; output is TensorFeed's curated ranking.

  ConnectorNo auth

• search_play_challengesA

  mcpA

  Return a list of hands-on SecDim Play secure coding challenges (labs) related to a detected or suspected vulnerability. SecDim Play challenges are scored, hands-on labs: find and fix a real vulnerability in running code to earn points and badges. Use this tool to: - Find hands-on SecDim Play labs for specific vulnerabilities like XSS, SQL Injection, etc. - Explore OWASP Top 10 vulnerabilities and related labs - Provide additional resources and guides to help developers improve their secure coding skills For structured tutorial content (text, video, and lab-based courses) on the same vulnerability, use search_learn_courses (SecDim Learn) instead or in addition. Args: search: Search term for the vulnerability (e.g., 'xss', 'sql-injection', 'injection') cwe: Common Weakness Enumeration (CWE) ID to filter by owasp: OWASP category to filter by (e.g., 'a03:2021') technology: Technology or framework to filter by (e.g., 'react', 'django') language: Programming language to filter by (e.g., 'javascript', 'python') difficulty: Difficulty level to filter by (e.g., 'trivial', 'easy', 'medium', 'hard') type: Challenge format to filter by (e.g., 'battle', 'exploitation', 'incident-response') mitre: MITRE ATT&CK ID to filter by (e.g., 'T1102.003') SecDim Play challenges (labs) each simulate a real vulnerability. They are scored according to the following difficulty levels: - Trivial: Easy to find and path vulnerabilities. It can be completed in 5-10 minutes. 1-15 points. - Easy: Known vulnerabilities. It can be completed in 10-30 minutes. 16-35 points. - Medium: Known vulnerabilities but require defence-in-depth patch. It can be completed in 20-30 minutes. 36-70 points. - Hard: Hard to find or patch vulnerabilities. It can be completed in 30-60 minutes. 71-100 points. - Battle: SecDim Flagship attack and defence challenge that require both vulnerability exploitation and mitigation skills. Points are accumulated. Returns: Dictionary containing SecDim Play labs results or error If there are no results, user can perform a manual search on the SecDim Play frontend (SECDIM_PLAY_FRONTEND_BASE_URL)

  ConnectorNo auth

• search_learn_coursesA

  mcpA

  Search SecDim Learn courses. SecDim Learn provides tutorial-based courses (mixing video, text and hands-on lab topics) covering secure coding, secure design, vibe coding security, devsecops, and cloud security. Many courses are complementary or prerequisite to hands-on, scored SecDim Play challenges/labs. Use this tool to: - Browse the SecDim Learn course catalogue - Find courses related to a topic, language, or technology (e.g. "OWASP Top 10", "fuzzing", "Python") Args: search: Optional search term to filter courses by title, description, or tags. If omitted, returns the full course catalogue. Returns: Dictionary with a "courses" list. Each course includes its title, description, image, slug, tags, numeric "level" (1=beginner, 2=intermediate, 3=advanced) and a "difficulty" label. Use get_learn_course with a course's slug to view its syllabus of topics.

  ConnectorNo auth

• search_placesA

  BinaSmartA

  Find buildings, hotels, hospitals and shops in Addis Ababa listed on BinaSmart (bina.et): cafés, restaurants, pharmacies, banks, gyms, salons, clinics, offices. Returns names (English + Amharic), building and unit, the phone only for shops that have claimed their listing, coordinates when known (usable as pickup/dropoff for quote_ride), and the bina.et page. Hotels and hospitals are flagged — use get_hotel_rooms / get_hospital_departments for details. For hospitals, clinics, dentists, labs and doctors anywhere in Addis Ababa, use search_health. For food (restaurants, cafes, a dish, "lunch near Megenagna") with no listed shop it returns map_place results from the city map: name, area, distance, coords and ride link, with no phone, hours, prices or menu (see map_note).

  ConnectorNo auth

• keyword_overviewA

  SearcherLiteA

  Search volume, CPC, keyword difficulty, competition, search intent and 12-month trend for one keyword (Google, via DataForSEO Labs). Cost: 1 credit. Free when no data exists for the keyword. Returns: the metrics for the keyword plus a monthly trend.

  ConnectorAPI key

• filter_by_industryA

  aetumiA

  Return EVERY AETumi Labs reference experience whose industry matches one exact value. AETumi Labs holds 31 live interactive reference experiences, published for study and reference; they are NOT catalog items for sale. Each result carries name, industry, experience type, visual styles, customer goals, live url and industry hub url. Accepted industry values: Agency & Portfolio, Automotive, Beauty & Cosmetics, E-commerce, Fashion, Finance & Fintech, Food & Beverage, Industrial, Music, Music & Entertainment, Real Estate, SaaS & Startup, Travel & Hospitality. Use this ONLY when you already hold one of those exact values and want the complete list for it. If the request mixes industry with another facet, or uses wording outside that list, use find_experiences instead. For commercial assets to license and ship, use search_3d_web_assets. Read-only, no authentication, no side effects; returns public metadata.

  ConnectorNo auth

• filter_by_styleA

  aetumiA

  Return EVERY AETumi Labs reference experience whose visual style matches one exact value. AETumi Labs holds 31 live interactive reference experiences, published for study and reference; they are NOT catalog items for sale. Each result carries name, industry, experience type, visual styles, customer goals, live url and industry hub url. Accepted visual style values: Bright Architectural, Cinematic Atmosphere, Cinematic E-commerce, Clean Studio, Dark Cinematic, Editorial Luxury, Experimental Creative, Glass & Holographic, Glass Luxury, High-Tech Product, Institutional Precision, Metallic Industrial, Minimal Futurism, Organic Premium, Premium Automotive, Premium Packaging, Soft Cinematic, Spatial Architecture, Spectral Neon, Technical Blueprint, Technical Precision. Use this ONLY when you already hold one of those exact values and want the complete list for it. If the request mixes visual style with another facet, or uses wording outside that list, use find_experiences instead. For commercial assets to license and ship, use search_3d_web_assets. Read-only, no authentication, no side effects; returns public metadata.

  ConnectorNo auth