Outscraper Mcp Server

Extract structured information from a web page with Outscraper AI Scraper. Best for: - scraping one page and turning it into structured JSON - extracting company, people, product, or document metadata from a site - guiding extraction with both a prompt and a JSON-schema-like shape This tool is best for extracting structured data from a single page. How schema works: - schema describes the shape of the output you want back - use type="object" with properties for named fields - use type="array" with items when a field should be a list - add required when some fields must be present Example schema: { "type": "object", "required": [], "properties": { "company_name": { "type": "string" }, "company_description": { "type": "string" }, "people": { "type": "array", "items": { "type": "string" } } } } Execution notes: - execution_mode="sync" requests a direct response - execution_mode="async" returns a request id for polling with requests_get - if both prompt and schema are provided, prompt guides the extraction and schema shapes the output

Search Outscraper businesses using structured filters, a natural-language query, or both. Best for: - building lead lists from normalized business records - filtering by country, state, city, type, and other structured business fields - paginated browsing with cursor when you want repeatable result navigation Prefer this tool when: - you already know the geography, categories, or other business filters you want - you want the normalized /businesses dataset rather than raw Google Maps search behavior - you need stable field selection and cursor-based pagination Use this instead of google_maps_search when: - you want the normalized /businesses API - you need field selection, filters, or cursor pagination Note: - according to the current OpenAPI, /businesses is a synchronous endpoint in this MCP server - async-style execution controls are intentionally not exposed here - structured filters are the most reliable input mode - live Outscraper testing showed that free-form query parsing may fail with "Could not parse query into a valid request format."

Get one business by Outscraper business id. Best for: - loading the full detail payload for a business found via businesses_search - fetching a smaller field-selected payload for one known business id Use this after businesses_search when you already know the exact business id. Do not use this for discovery: - use businesses_search to find records first - then call businesses_get for the exact item you want to enrich or inspect

Search Google Maps places through Outscraper. Best for: - ad hoc place discovery from one or more Google Maps queries - cases where the user thinks in Google Maps terms rather than /businesses filters - retrieving place results directly from the Google Maps search pipeline Prefer this tool when: - the user gives Google Maps-style queries such as "restaurants brooklyn usa" - you want place discovery without building structured business filters first - you want async submissions for larger query batches or enriched Google Maps searches Use businesses_search instead when: - you want normalized businesses filters or cursor pagination - you want to combine strict filters with natural-language business search Use execution_mode="auto" when: - there are multiple queries - the limit is high - enrichments are requested

Fetch Google Maps reviews for place ids or place queries. Best for: - review analysis - recent-review monitoring - targeted review extraction for specific places Prefer this tool when: - the user needs review text, review counts, or review metadata - you already know the place or can identify it from a query - async polling is acceptable for heavier review jobs Use async mode when: - review volume is large - you query many places in one request - you want to poll progress later with requests_get Do not use this for basic place discovery: - use google_maps_search first - then use google_maps_reviews once you know the target place or query set

Fetch Google Maps photos with the documented /google-maps-photos endpoint. Best for: - place photo extraction - menu photo retrieval - owner photo and latest photo analysis

Search Google with the documented /google-search endpoint.

Search Google Images with the documented /google-search-images endpoint.

Search Yellowpages with the documented /yellowpages-search endpoint.

Search Indeed with the documented /indeed-search endpoint.

Search Tripadvisor with the documented /tripadvisor-search endpoint.

Fetch Booking reviews with the documented /booking-reviews endpoint.

Fetch Yelp reviews with the documented /yelp-reviews endpoint.

Fetch Tripadvisor reviews with the documented /tripadvisor-reviews endpoint.

Legacy alias for trustpilot_data. Prefer trustpilot_data for new integrations.

Fetch Trustpilot business data with the documented /trustpilot endpoint.

Legacy alias for trustpilot_reviews. Prefer trustpilot_reviews for new integrations.

Fetch Trustpilot reviews with the documented /trustpilot-reviews endpoint.

Validate email addresses with the documented /email-validator endpoint. Best for: - deliverability checks - validating outbound lead lists - filtering invalid email inputs before enrichment or outreach

Enrich phone numbers using the documented /phones-enricher endpoint. Best for: - carrier lookup - phone validation - message deliverability checks Note: this endpoint is synchronous only and does not support async execution or webhooks.

Detect chain membership using the documented ai_chain_info enrichment. This tool uses the documented enrichment on top of the Google Maps search pipeline. Use it when you want to know whether a business is part of a chain.

Get structured company-level insight data from Outscraper. Best for: - enriching known companies or domains - pulling structured company metadata instead of raw search results - larger async enrichment jobs that can be tracked later with requests_get Prefer this tool when: - the user already has domains or company URLs - the goal is firmographics, company profile data, size, revenue, industry, or founding details - you want structured company enrichment rather than contact extraction Use async mode when: - you send many companies at once - the endpoint is expected to do expensive enrichment work Use emails_and_contacts instead when: - the user mainly wants emails, phones, socials, or people/contact data - company profile enrichment is secondary to lead/contact discovery Returns: - direct response payload in sync mode - async request metadata in async mode

Find emails, phones, and social/contact data from one or more company domains. Best for: - domain-based lead enrichment - finding reachable company contacts from a known website - quick contact discovery before running heavier enrichment flows Prefer this tool when: - the user already knows the company website or domain - the main goal is contact discovery rather than company metadata - you want emails, phones, socials, and website-derived contact details Use async mode when: - you send many domains at once - you expect the crawl/enrichment to take longer - you want to track progress later with requests_get Use company_insights instead when: - the user wants firmographics, company profile, revenue, size, or founding details - contact data is not the main objective

Check whether the Outscraper MCP server is running and return basic server metadata. Best for: - validating local or container startup - confirming the MCP server is reachable before making live API calls - lightweight health checks in demos, IDE setups, or registry validation

Fetch the current Outscraper account balance and billing summary for the active API key. Best for: - checking whether the key is attached to a funded account - confirming account status before running larger jobs - reading upcoming invoice and usage billing details Use this when: - you want a quick health check for the current API key/account - you need to confirm available balance before large async jobs - you are debugging whether billing or account status might explain API behavior

Check the status of an asynchronous Outscraper request. Use this after calling any tool with execution_mode="async" or after an auto-selected async submission. Typical flow: 1. call google_maps_reviews, company_insights, emails_and_contacts, or google_maps_search with execution_mode="async" 2. capture the returned request id 3. poll requests_get until the job is completed or failed Use this tool when: - a previous tool returned an async request id - you want to know whether the request is Pending, Success, or Failure - you need the completed data from a previously submitted async job

List recent Outscraper requests by bucket. Best for: - debugging async flows - seeing running, completed, or failed jobs - checking what was recently submitted through the current API key Use this when: - you lost a request id and want to find recent jobs - you want a quick view of recent running or finished requests - you are debugging async submissions across tools

Delete or terminate an asynchronous Outscraper request by request id. Best for: - cleaning up queued or no-longer-needed async jobs - stopping work you no longer want to keep polling - testing the full async request lifecycle from MCP Use this carefully: - it is intended for cleanup or cancellation - only use it when you are sure the request is no longer needed - after deletion, the original async request should not be expected to complete normally