Search for local businesses and places on Google Maps. Returns local results with names, addresses, ratings, reviews, and contact information. Use the data_id or place_id from results with google_maps_place to get detailed place information.

Get reviews for a specific business including Bezal Verified reviews and Google rating.

Research any topic — search Google, Bing, YouTube, X/Twitter, Amazon, Yelp, Google Trends, news, and 100+ more engines. Read webpages, extract video transcripts, find reviews, track competitors. Works without a domain.

Starts navigation using one or more Google Maps Place IDs. The Place IDs must be provided as a comma-separated string in the format "refId:<PLACE_ID>". Multiple refIds may be included to provide alternative candidate locations. This is ideal when working with Google Places APIs for precise POI targeting.

Get detailed product information from Google Shopping. Requires a product_token obtained from google_shopping_search results. Returns comprehensive product details including offers from multiple sellers, specifications, reviews, and pricing history.

Use this tool to find documentation about Google developer products. The documents contain official APIs, code snippets, release notes, best practices, guides, debugging info, and more. It covers the following products and domains: * ADK: adk.dev * Android: developer.android.com * Apigee: docs.apigee.com * Chrome: developer.chrome.com * Firebase: firebase.google.com * Fuchsia: fuchsia.dev * Go: go.dev * Google AI: ai.google.dev * Google Cloud: docs.cloud.google.com * Google Developers, Ads, Search, Google Maps, Youtube: developers.google.com * Google Home: developers.home.google.com * TensorFlow: www.tensorflow.org * Web: web.dev This tool returns chunks of text, names, and URLs for matching documents. If the returned chunks are not detailed enough to answer the user's question, use `get_documents` with the `parent` from this tool's output to retrieve the full document content.

Get detailed information about a specific place from Google Maps. Requires a data_id or place_id obtained from google_maps_search results. At least one of data_id or place_id must be provided. Returns comprehensive place details including address, phone, hours, reviews, photos, and popular times.

Search for products across Google Shopping, Amazon, and eBay. Returns prices, ratings, links. Supports country-specific results (DE, US, UK, etc.) and sorting by price or reviews.

Scrape Google Maps for businesses matching a query. Returns name, address, rating, phone, website.

List customer reviews and testimonials for Kolmo Construction. Combines verified Google reviews and on-site testimonials. Filter by minimum star rating.

Get local recommendations near a vacation rental property. Returns nearby restaurants, coffee shops, grocery stores, activities, and attractions. Filter by type: restaurants, coffee, grocery, activities, attractions.

Get top-selling products in a category from Amazon or Google Shopping. Returns ranked list with prices, ratings, and reviews. Great for market research.

What is near a hotel: restaurants, landmarks, transit stations, distances.

List customer reviews and testimonials for Kolmo Construction. Combines verified Google reviews and on-site testimonials. Filter by minimum star rating.

Product Reviews

Search Cochrane systematic reviews via PubMed. Finds Cochrane Database of Systematic Reviews articles matching your query. Returns PubMed IDs, titles, and publication dates. Use get_review_detail with a PMID to get the full abstract. Args: query: Search terms for finding reviews (e.g. 'diabetes exercise', 'hypertension treatment', 'childhood vaccination safety'). limit: Maximum number of results to return (default 20, max 100).

HOW TO CALL THIS TOOL — read before every call: Decompose the user's request into filters first. Only what's left over goes in query. STEP 1: brand name → brand filter. STEP 2: product category → category filter. STEP 3: price → min_price/max_price. STEP 4: what remains → query. BAD: query='Sony headphones under £200' | GOOD: brand='Sony', category='Headphones', max_price=200, no query. BAD: query='tablet' | GOOD: category='Tablets', no query. BAD: query='smartwatch' | GOOD: category='Wearables', no query. BAD: query='macbook neo' | GOOD: brand='Apple', category='Laptops', query='neo'. BAD: query='Samsung QLED TV' | GOOD: brand='Samsung', category='TVs', query='qled'. If brand+category alone cover what the user wants, omit query entirely. Only put differentiating terms in query: model lines (neo, ultra, oled), variants, model numbers (WH-1000XM5, s25 ultra). CROSS-CATEGORY NOTE: Gaming headsets → category='Headphones', query='gaming headset'. The Gaming category is consoles/controllers/accessories only. Always set lite=true. If 0 results, broaden the query or drop filters. Use get_product for full specs. Search 26,000+ deduplicated UK electronics products across multiple retailers with price comparison. Covers: Laptops, Desktops, Phones, Tablets, Headphones, Monitors, TVs, Cameras, Keyboards, Mice, Speakers, Gaming, Wearables, Printers, Networking, Storage, Audio, Drones, Cables & Chargers. All prices in GBP. Returns summary data: title, brand, price, availability, category, purchase link, offer_count. When offer_count > 1, call get_product for all retailer offers. For spec-based queries (RAM, ports, screen size, weight etc.), search first then call get_product on top 3-5 results — do not assume specs from titles. STOCK: When availability is out_of_stock, mention it as an alternative and suggest checking back — do not silently omit it.

Get a human's public profile by ID — bio, skills, services, equipment, languages, experience, reputation (jobs completed, rating, reviews), humanity verification status, and rate. Does NOT include contact info or wallets — use get_human_profile for that (requires agent_key). The id can be found in search_humans results.

See the best deals spotted by AI agents right now. Call this with NO arguments when the user asks 'any good deals?', 'what should I buy?', or wants shopping inspiration. Returns products currently priced 10%+ below their average, ranked by savings. Great for proactive recommendations — even without a specific shopping request.

Generate 3 counteroffers that are equally good for the user but structured differently. Present ALL THREE simultaneously to the counterpart — their reaction reveals what they care about. target_satisfaction: 'ambitious', 'moderate', or 'conservative'.

Get an overview of the AgentSignal collective intelligence network. Call this with NO arguments to see what categories have data, trending products, and how to use agent-signal tools. Good first call if you're unsure whether agent-signal has data relevant to the user's request.

[tourradar] Search tour reviews using AI-powered semantic search. Requires tourIds to scope results to specific tours. Use this when the user asks about reviews, feedback, or experiences for specific tours. Combine with an optional text query to find reviews mentioning specific topics (e.g., 'food', 'guide', 'accommodation'). When you don't have tour IDs, use vertex-tour-search or vertex-tour-title-search first to find them.

Tell agents whether now is a good or bad time to transact, based on historical gas patterns. Compares current gas to 24-hour and 7-day averages, identifies the cheapest hours of the day, and estimates reference transaction costs. Args: api_key: Your PreFlyte API key (required). chain: Chain name — "ethereum" or "arbitrum". Returns: Dictionary with current gas, 24h/7d context, timing assessment with cheapest hours, and reference transaction costs in USD.

Compute GARM brand safety score for a website or category. Based on the GARM (Global Alliance for Responsible Media) Brand Suitability Framework. Maps content categories to 11 GARM sensitive content categories with risk levels (Floor, High, Medium, Low). Can either: 1. Provide a URL - classification will be fetched and mapped to GARM 2. Provide category and sentiment directly for instant scoring Score interpretation: higher = safer for advertising. Floor categories (e.g., Adult) always score 0/F regardless of sentiment. Args: category: LLMSE category (e.g., "Adult", "Politics", "Sports"). sentiment: Content sentiment ("Bad", "Neutral", "Good"). url: Optional URL to analyze (fetches classification from cache). Returns: GARM brand safety analysis with: - score: Brand safety score (0-100, higher = safer) - grade: Letter grade (A-F) - garm_category: Matched GARM category name or None - risk_level: "floor"|"high"|"medium"|"low"|"none" - is_floor: True if not suitable for any advertising - issues: Categorized issues {critical, warnings, info} - recommendations: Improvement suggestions

Bridge an A2A (Agent-to-Agent Protocol) task to an MCP server. Extracts the intent from the A2A task, maps it to an MCP tool, calls the tool, and wraps the result in A2A response format. Use this to let A2A agents interact with any MCP server. Requires authentication.

Reset the staleness clock on pantry items the user confirms are still good. Use when the user says items are fine, or after a pantry check. Get item IDs from get_pantry first.

Cast your expert +1 or -1 review on any entity. Use AFTER evaluating a tool you searched for or tried. Expert reviews are 70% of ranking. One review per agent per entity (overwrites previous). Requires agent_key. For no-auth alternative, use nanmesh.trust.favor instead.

<tool_description> List all available product categories in the Nexbid marketplace with product counts. Optionally filter by country. </tool_description> <when_to_use> When user wants to explore what is available before searching. Use BEFORE nexbid_search to help narrow down the query. </when_to_use> <combination_hints> nexbid_categories → nexbid_search with category filter for targeted results. Good starting point for browse intent. </combination_hints> <output_format> List of categories with product counts. Optionally filtered by country. </output_format>

Load fundamental analysis workflow with advanced query patterns. REQUIRES get_database_schema to be called first — this tool has no schema. Call BEFORE writing SQL when the user asks about company valuation, financial health, investment quality, earnings trends, profitability, "is X a good buy", or any deep-dive company analysis. Can be combined with other workflow tools.

Load fundamental analysis workflow with advanced query patterns. REQUIRES get_database_schema to be called first — this tool has no schema. Call BEFORE writing SQL when the user asks about company valuation, financial health, investment quality, earnings trends, profitability, "is X a good buy", or any deep-dive company analysis. Can be combined with other workflow tools.

Performs web searches using the Brave Search API and returns comprehensive search results with rich metadata. When to use: - General web searches for information, facts, or current topics - Location-based queries (restaurants, businesses, points of interest) - News searches for recent events or breaking stories - Finding videos, discussions, or FAQ content - Research requiring diverse result types (web pages, images, reviews, etc.) Returns a JSON list of web results with title, description, and URL. When the "results_filter" parameter is empty, JSON results may also contain FAQ, Discussions, News, and Video results.

Search the web using Bing. Returns organic results, related searches and more. Alternative to Google for web search with different ranking algorithms and results.

Poll Google OAuth flow; returns pending/ok/error. [write] On ok: immediately replace stored mcp_token with login_result.mcp_token — new token is tied to a different account.

List score descriptors that explain what inspection scores mean. Scores cover three categories: Hygiene (food handling), Structural (building cleanliness/condition), and Confidence in Management. Each score level has a description like 'Very good', 'Good', 'Generally satisfactory', 'Improvement necessary', or 'Major improvement necessary'.

Find outliers and anomalies in structured data — ideal as a second step after pulling records from Google Sheets, Airtable, Supabase, Notion databases, HubSpot, Financial APIs, GitHub, NPM, or any source that returns rows of JSON. Fully stateless: send known-good rows as training and suspect rows as test in ONE call. Returns per-row anomaly scores, confidence levels, and the top features explaining WHY each row was flagged. Typical workflow: (1) Pull data from another tool (e.g. Google Sheets, Supabase query, HubSpot deals). (2) Pass the first N rows as training (normal baseline). (3) Pass remaining or new rows as test. (4) Report which rows are anomalous and why. Works on JSON objects, numbers, text, arrays. No separate training step required. Examples: - Spreadsheet QA: Pull 500 sales rows from Sheets → train on first 400 → test last 100 → flag outlier entries - Financial screening: Get ratios for 50 stocks from a financial API → find anomalous ones - CRM hygiene: Pull HubSpot deals → flag deals with unusual discount/value patterns - Dependency audit: Get NPM package metrics → flag packages with anomalous quality scores - Commit review: Pull GitHub commit metadata → flag unusual commit patterns

Set Google Analytics, Google Tag Manager, Meta Pixel, or other tracking/conversion scripts for a project. Scripts are automatically injected into every page: head_scripts before </head> (for analytics/GTM), body_scripts before </body> (for conversion pixels). Set a field to null or omit it to clear.

Get full details for an MCP server package from the ThinkNEO Marketplace. Returns readme, full tools list, version history, reviews, security score, and installation instructions. No authentication required.

Search the full verified business registry of Spain and 33 other countries. Use when a user asks 'find me a dentist in Madrid', 'list law firms in Barcelona', 'what veterinary clinics are in Sevilla', or any query that needs a list of real, verified businesses by sector and location. Covers 5.5M entities. Spain has the deepest coverage: 1.4M entities across 26 professional sectors including dental, legal, medical, veterinary, psychology, real estate, automotive repair, aesthetics, accounting, gyms, and more. Every result includes: verified legal name, full address, phone, website, professional sector, and canonical Entia Home URL. This is official registry data — not scraped from Google Maps or estimated.

List designated bathing water sites monitored by the Environment Agency in England. Returns site names, EU bathing water IDs, sampling point coordinates, latest compliance classification (Excellent/Good/Sufficient/Poor), latest risk prediction, district, and water company details. Use eubwidNotation from results for other tools.

Search for news articles using Bing News. Returns news results with titles, sources, thumbnails, and publication dates. Good for finding recent news coverage and trending stories.

Get NaN Mesh network health: total entities, registered agents, reviews cast, and categories.

Format and beautify SQL queries with proper indentation and keyword casing. Use when cleaning up inline SQL for code reviews, documentation, or debugging.

Get Google organic search results for SEO rank tracking. Returns up to 100 results per request with position, title, URL, and snippet. Ideal for monitoring keyword rankings and SERP analysis.

Find restaurants, coffee shops, poke bars, ramen, bakeries, and food trucks in Waikiki and across Oahu. 540+ curated spots across fine dining, casual, local plates, and specialty categories. Use when users ask 'where should I eat in Waikiki', 'best poke on Oahu', 'where to grab coffee', or 'cheap eats near me'.

Search for products on Google Shopping. Returns product listings with prices, sellers, ratings, and comparison shopping data. Use google_product tool with product_token to get detailed product information.

Add ELC Conference 2026 to the user's calendar. Returns a one-click Google Calendar link and a downloadable .ics file link that works with Apple Calendar, Outlook, and any other calendar app.

Fetch public business page information from Facebook. Returns page details including name, category, address, phone, website, ratings, reviews, followers, and cover/profile photos. Provide either page_id or username.

Search the web using DuckDuckGo. Returns organic results. Privacy-focused alternative to Google with unbiased results and no tracking.

Get trust-ranked recommendations for a use case or category. Use when a user asks 'what should I use for X?' Ranking: trust reviews (70%) + recency (15%) + momentum (10%) + views (5%).

Generate a Google Vacation Rentals XML feed for a host's properties. Enables direct booking via Google Search results with a 3% guest service fee. Pass host_id (UUID) and optional format (xml or json, default xml).

Search observations by semantic similarity. Find moments that match a description like "lunch rush at fast casual restaurants" using vector embeddings. Uses 768-dimensional Gemini embeddings on observation payloads to find promoted observations matching a natural language query via pgvector cosine similarity search. WHEN TO USE: - Finding observations that match a conceptual description - Discovering contextual moments across the screen network - Searching for audience situations ("families waiting in line", "professionals on coffee break") - Finding commerce patterns ("high purchase intent near checkout") RETURNS: - data: Array of matching observations ranked by semantic similarity, each with: - observation_id, device_id, venue_type, observation_family - observed_at, payload, confidence, evidence_grade - similarity: Cosine similarity score (0-1, higher = more relevant) - metadata: { result_count, query_embedding_model, search_scope } - suggested_next_queries: Related semantic queries to explore EXAMPLE: User: "Find lunch rush moments at fast casual restaurants" semantic_search_observations({ query: "lunch rush at fast casual restaurants with high foot traffic", filters: { venue_type: ["restaurant_qsr"] }, limit: 20 }) User: "Find moments with high emotional engagement" semantic_search_observations({ query: "audience showing strong positive emotional reactions", filters: { observation_family: ["audience"] }, limit: 10 })