Crawlora MCP

Crawlora MCP is a hosted Model Context Protocol server that gives AI clients and agents 3625 structured public‑web‑data tools across 471 platform groups — search, maps, e‑commerce, social, finance, travel, app stores, media, and reviews — each returning clean, normalized JSON instead of HTML to parse.

Two ways to use it: connect any MCP client to the hosted endpoint (https://mcp.crawlora.net/mcp), or run the small open‑source local server in this repo (npx / Docker, stdio) — both expose the same tools and authenticate with your Crawlora API key. Start free with 2,000 credits/month (no card) at crawlora.net.

Connection

Endpoint	https://mcp.crawlora.net/mcp
Transport	Streamable HTTP
Auth	Authorization: Bearer <CRAWLORA_API_KEY> (preferred) — x-api-key: <key> also accepted
Get a key	https://crawlora.net (free 2,000 credits/mo)
Server card	https://crawlora.net/.well-known/mcp/server-card.json

A missing or invalid API key returns 401.

Connect your client

Crawlora MCP works with any MCP‑capable client. Pick yours below — they all point at the same hosted endpoint (https://mcp.crawlora.net/mcp, Streamable HTTP) and authenticate with your CRAWLORA_API_KEY. Prefer keeping the key in an environment variable over pasting it literally, and never commit it. Ready‑to‑paste files for each client live in examples/.

Claude Code (CLI)

claude mcp add --transport http crawlora https://mcp.crawlora.net/mcp \
  --header "Authorization: Bearer ${CRAWLORA_API_KEY}"

Adds at local scope by default. Use --scope user to make it available in every project, or --scope project to write a shared .mcp.json. Confirm with claude mcp list.

Claude Desktop

Settings → Developer → Edit Config, then add to claude_desktop_config.json:

{
  "mcpServers": {
    "crawlora": {
      "url": "https://mcp.crawlora.net/mcp",
      "transport": "streamable-http",
      "headers": { "Authorization": "Bearer YOUR_CRAWLORA_API_KEY" }
    }
  }
}

Cursor

Project‑local .cursor/mcp.json (or ~/.cursor/mcp.json for all projects):

{
  "mcpServers": {
    "crawlora": {
      "url": "https://mcp.crawlora.net/mcp",
      "headers": { "Authorization": "Bearer ${CRAWLORA_API_KEY}" }
    }
  }
}

Codex CLI

codex mcp add crawlora \
  --url https://mcp.crawlora.net/mcp \
  --bearer-token-env-var CRAWLORA_API_KEY

VS Code (GitHub Copilot)

.vscode/mcp.json (project) or your user mcp.json:

{
  "servers": {
    "crawlora": {
      "type": "http",
      "url": "https://mcp.crawlora.net/mcp",
      "headers": { "Authorization": "Bearer ${env:CRAWLORA_API_KEY}" }
    }
  }
}

Windsurf

~/.codeium/windsurf/mcp_config.json (note the serverUrl key):

{
  "mcpServers": {
    "crawlora": {
      "serverUrl": "https://mcp.crawlora.net/mcp",
      "headers": { "Authorization": "Bearer ${env:CRAWLORA_API_KEY}" }
    }
  }
}

Gemini CLI

~/.gemini/settings.json (note the httpUrl key):

{
  "mcpServers": {
    "crawlora": {
      "httpUrl": "https://mcp.crawlora.net/mcp",
      "headers": { "Authorization": "Bearer YOUR_CRAWLORA_API_KEY" }
    }
  }
}

Cline / Roo Code

Add to cline_mcp_settings.json using the generic remote shape — full walkthrough in llms-install.md:

{
  "mcpServers": {
    "crawlora": {
      "url": "https://mcp.crawlora.net/mcp",
      "transport": "streamable-http",
      "headers": { "Authorization": "Bearer ${CRAWLORA_API_KEY}" }
    }
  }
}

Other clients

Any client that speaks Streamable HTTP can use the generic config in examples/mcp.json. stdio‑only clients (e.g. Zed) should run the local server below and point at its npx command.

Run it locally (open‑source server)

This repo also ships a small stdio MCP server (index.mjs) that exposes the same 3625 tools, each wrapping the Crawlora REST API (https://api.crawlora.net/api/v1) with your CRAWLORA_API_KEY. Useful if you'd rather run the server yourself than use the hosted endpoint.

The counts above describe this repository’s current source catalog. The npm package used by npx crawlora-mcp may contain the previous catalog until a tagged release is published. To use this source snapshot, clone the repository and follow the local setup instructions below.

# Node 20+ (no install)
CRAWLORA_API_KEY=your-key npx -y crawlora-mcp

# or from a clone
npm install && CRAWLORA_API_KEY=your-key node index.mjs

# or Docker
docker build -t crawlora-mcp . && docker run -i -e CRAWLORA_API_KEY=your-key crawlora-mcp

Client config (stdio):

{
  "mcpServers": {
    "crawlora": {
      "command": "npx",
      "args": ["-y", "crawlora-mcp"],
      "env": { "CRAWLORA_API_KEY": "your-key" }
    }
  }
}

The tool definitions in tools.json are generated from Crawlora's published API catalog; each carries its real input schema and maps to a single REST endpoint.

Hosted MCP (recommended)

Just paste the URL into your client settings. No Node.js required.

https://mcp.crawlora.net/mcp

Header: x-api-key: <your-api-key>

Get a key at crawlora.net. Every account includes 2,000 free credits / month with no credit card required.

---

Tools

The complete tool catalog is generated from tools.json so MCP directories can index it.

abcau_article

Get ABC News Australia article content. Returns public ABC News Australia article metadata and body paragraphs from a canonical article URL.

abcau_author

Get an ABC News Australia author profile. Returns an ABC News Australia author's byline metadata, biography, and recent articles from a canonical author URL.

abcau_headlines

Get ABC News Australia section headlines. Returns fresh headlines from one public ABC News Australia section.

abcau_news

Get ABC News Australia top stories. Returns fresh ABC News Australia top stories from its public RSS feed.

abcau_sections

Get ABC News Australia sections. Returns the public ABC News Australia section inventory used by the headlines endpoint.

abcnews_article

Get ABC News article content. Returns public ABC News article metadata and body paragraphs from a canonical article URL. Accepts both the "story?id=..." and "wireStory/..." canonical URL shapes.

abcnews_author

Get an ABC News author profile. Returns an ABC News author's profile: name, job title/biography when the page carries one, and social links, from a canonical author URL. Does NOT include a list of the author's recent articles -- unlike this repo's other news-author endpoints, ABC News only exposes that list through an internal endpoint disallowed for every crawler in abcnews.com's robots.txt (a generic "Disallow: /proxy/*" rule, not limited to AI-training bots), so it is out of scope for this endpoint.

abcnews_headlines

Get ABC News section headlines. Returns fresh headlines from one ABC News section's public hub page.

abcnews_news

Get ABC News top stories. Returns fresh ABC News top stories from its public news sitemap feed.

abcnews_sections

Get ABC News sections. Returns the ABC News section inventory: the 8 core news sections accepted by abcnews-headlines.

accor_amenities

Accor amenity reference catalog. Returns the anonymous public Accor amenity catalog with stable amenity codes, labels, categories, and display ordering. It is reference data for interpreting hotel search facets; booking, rates, rooms, reviews, and account data are excluded.

accor_brands

Accor brand directory. Returns the Accor brand directory published on the public brands page, with each brand's name, slug, and source URL. Booking, rates, rooms, reviews, contacts, and location are excluded.

accor_catalog_hotels

Search the Accor hotel catalog. Searches Accor's anonymous public hotel catalog by text, hotel code, or latitude/longitude radius. Results contain static property identity and broad location metadata plus catalog relevance/distance; contact details, precise hotel coordinates, payment, loyalty, media, rates, rooms, reviews, and booking data are excluded.

accor_destination_hotels

Accor hotels in a destination. Returns the static list of hotels published on one Accor destination directory page (world, continent, country, region, department, city, district, or place), optionally narrowed by a theme facet. Each hotel carries its code, name, source URL, and broad city/country. Booking, rates, rooms, reviews, contacts, and precise location are excluded.

accor_property

Accor hotel metadata. Returns static public metadata for one Accor hotel code, including name, brand, city/country, explicitly listed amenities, and published check-in/check-out times. Booking, rates, rooms, reviews, contacts, and precise location are excluded.

accor_search

Search Accor hotels. Searches the public Accor hotel index by destination or hotel name, with optional country, city, brand, star, page, and page-size filters. Results contain static hotel identity, location labels, ratings, and source URLs; booking, rates, rooms, reviews, loyalty, and payment flows are excluded.

accor_search_details

Accor place coordinates and viewport. Resolves an anonymous Accor search suggestion identifier to its description, coordinates, viewport, radius, and address components. It uses the same public place-details source as the Accor search box; booking, rates, rooms, reviews, and account data are excluded.

accor_search_suggest

Accor destination and hotel search suggestions. Returns anonymous Accor typeahead suggestions for a partial destination or hotel query, including destination/place and hotel identifiers, types, labels, and match metadata. It uses the public search-box suggestion source only; booking, rates, rooms, reviews, and result-list requests are excluded.

adidas_product

Get an Adidas product. Returns normalized product-detail data for one Adidas SKU: name, brand, category, description, pricing (current/standard/sale), images, and every purchasable size variant. product_id is the Adidas SKU (e.g. JI0397), taken from a search result's products[].id field or the trailing segment of an Adidas product page URL. An unknown product_id returns a not-found error.

adidas_product_review_topics

Get Adidas review topics for a product. Returns the topics an Adidas product model's customer reviews can be filtered by -- the "filter by topic" chips the product page shows, commonly satisfaction, comfort, color, purchase, fit, appearance, quality and style. Feed a topics[].topic value back to /adidas/product/reviews as its topic parameter to return only reviews about that aspect. The topic vocabulary is per model, not a fixed list: a shoe exposes fit and comfort topics that an accessory does not, so read it per model rather than hard-coding it. model_number is the Adidas model number (e.g. SAMBAU2312) -- NOT the SKU: take it from an adidas_search result's products[].model_number field. A model with no reviews, including a well-formed but unrecognized model_number, returns an empty topics list rather than an error. Note the label field is a display form of topic, not translated text: Adidas returns the same English values for every locale on this route.

adidas_product_reviews

Get Adidas product reviews. Returns one page of customer reviews for an Adidas product model, plus the model's rating summary: overall rating, star histogram, percentage of reviewers who recommend it, per-attribute averages (Size, Width, Comfort, Quality with their own scale labels), and Adidas's AI-generated review digest when one exists. Each review carries the rating, headline, body, author nickname, purchased colorway, helpful/not-helpful vote counts, badges, customer photos, and submission time. model_number is the Adidas model number (e.g. SAMBAU2312) -- NOT the SKU: take it from an adidas_search result's products[].model_number field, which is a different value from products[].id. Reviews are returned 10 per page. Reviews are scoped to review text written in the requested locale's language, and most of the US catalog's reviews are English, so a non-English locale commonly returns rating statistics and a localized summary with an empty reviews list. A model with no reviews -- including a well-formed but unrecognized model_number -- returns an empty reviews list rather than an error, because Adidas answers 200 with a zero count rather than 404.

adidas_search

Search or browse Adidas products. Searches Adidas.com product listings by keyword, or browses a category listing by taxonomy slug, with real pagination and sort options. Exactly one of query or category is required. Returns normalized product summaries (title, price, rating, images, color variants) plus facet filter groups, sort options, and (for category browse) a breadcrumb trail. Keyword search is best-effort relevance, not a guaranteed match: an obscure keyword returns whatever Adidas's own search index surfaces. A genuinely empty keyword search returns an empty product list, and requesting a page beyond the available result pages (or an unknown category) returns a not-found error. Category values are the path segment after /us/ in an Adidas category URL (e.g. women-athletic_sneakers); they can also be read from the url fields of a search/category response's own filters and breadcrumbs. Facets are applied by composing them into the category slug rather than by a separate parameter: each filters[].values[].slug is a token you splice into the category value (e.g. category=women-black-athletic_sneakers applies the Color=Black facet, and category=women-athletic_sneakers-prime applies Shipping=PRIME). Use filters[].key (the facet's stable name, e.g. searchcolor) rather than filters[].id, which is an opaque per-deployment UUID that cannot be used to build a request. Note the token's position within the slug varies by facet, so compose from a slug you have seen rather than assuming a fixed order.

adidas_store

Get an Adidas store. Returns normalized detail for one Adidas retail store: name, status, phone, description, full address, coordinates, opening hours, and in-store services (e.g. Click and Collect, Free Wi-Fi). store_id is the numeric Adidas store id, taken from an adidas-stores response's stores[].id field. An unknown store_id returns a not-found error.

adidas_stores

Find nearby Adidas stores. Returns Adidas physical retail stores nearest to a coordinate, sourced from Adidas's own store-finder API: name, address, phone, coordinates, distance in miles, opening hours, and in-store feature flags. lat and lng are both required. Adidas's upstream ignores a caller-supplied radius and returns the nearest ~20 stores ordered by distance. A location with no stores returns an empty list rather than an error.

adidas_suggest

Get Adidas search suggestions. Returns the top matching products for a partial query, the same search-as-you-type preview Adidas's own search box shows. Adidas has no separate term-autocomplete index, so each suggestion is a matching product (id, title, url, image, price) rather than a completed search phrase. Best-effort relevance: an obscure query returns whatever Adidas's own search surfaces.

agoda_activities_search

Search Agoda activities. Returns Agoda activities (tours, attractions, experiences) matching a free-text keyword and/or a city. When keyword is omitted, the resolved city's name is used instead to return a general listing of activities in that city. Callers may supply a known Agoda city id or a free-text city name for the city filter; when both are supplied city_id takes precedence. Credential-free public data from Agoda's own destination search.

agoda_activity_detail

Get Agoda activity detail. Returns full activity detail from Agoda: title, description, stated duration, categories, and content images. Credential-free public data from Agoda's own activity content source.

agoda_flights_itinerary_amenities

Get Agoda flight segment amenities. Returns real-content amenities (aircraft type, seat layout, meals, entertainment, wifi) for one or more flight segments. Copy the segments straight from a flight search response's own segment fields. Credential-free public data from Agoda's own flight content service.

agoda_flights_search

Search Agoda one-way flights. Returns bookable one-way flight itineraries between two IATA airport codes for a departure date, including per-segment flight number, airline, times, layovers, aircraft type, and price. Resolve free-text city/airport names to codes first via the flight destination search endpoint. Credential-free public data from Agoda's own flight search.

agoda_flights_search_locations

Search Agoda flight destinations/airports. Resolves a free-text city or airport name into IATA airport codes for flight search, with each city's direct and nearby airports. Credential-free public data from Agoda's own flight destination search.

agoda_homes_search

Search Agoda Homes & Apartments by city. Returns Homes & Apartments results for an Agoda city: full listing detail for every matching property whose accommodation type is Apartment, drawn from the same city search as hotel search and filtered to non-hotel accommodation types. Callers may supply a known Agoda city id or a free-text city name; when both are supplied city_id takes precedence. Credential-free public data from Agoda's own hotel/home search.

agoda_hotel_detail

Get Agoda hotel detail. Returns full hotel detail from Agoda: identity (name, any former name), an accommodation type code, address (street address, postal code, city, country), guest rating, a main photo, room count, hotel chain id, a long and short description, and short-form policy statements (minimum age, adult/child definitions, extra-bed and additional-room booking policy). Credential-free public data from Agoda's own hotel content source.

agoda_hotels_search

Search Agoda hotels by city. Returns hotel search results for an Agoda city: the matching property ids for that city plus a direct link to each property's listing page. Callers may supply a known Agoda city id or a free-text city name; when both are supplied city_id takes precedence. Credential-free public data from Agoda's own hotel search.

airbnb_host

Get Airbnb host profile. Returns a normalized Airbnb public host profile — display name, Superhost and identity-verification status, location, bio, hosting tenure, total guest-review count, and total listing count.

airbnb_host_listings

Get Airbnb host listings. Returns the listings an Airbnb host manages, paginated. Page 1 comes from the host profile; deeper pages page through the host's full portfolio.

airbnb_host_reviews

Get Airbnb host reviews. Returns reviews guests left for an Airbnb host, paginated, including the reviewer name and location.

airbnb_room

Get Airbnb room. Returns normalized Airbnb public room details.

airbnb_room_calendar

Get Airbnb room calendar. Returns public calendar month hints parsed from Airbnb room bootstrap data.

airbnb_room_reviews

Get Airbnb room reviews. Returns normalized Airbnb public review snippets.

airbnb_search

Search Airbnb stays. Returns normalized Airbnb public web search results.

alcom_headlines

Get AL.com section headlines. Returns current headlines from one of AL.com's public Arc RSS section feeds. Summaries are brief publisher teasers, not full article text.

alcom_news

Get AL.com top stories. Returns current AL.com News stories from its public Arc RSS feed. Feed summaries are brief publisher teasers, not full article text.

alcom_sections

Get AL.com editorial sections. Returns the three top-level editorial sections exposed in AL.com's site navigation and accepted by the headlines endpoint.

aliexpress_reviews

Get AliExpress product reviews. Returns one page of public reviews and rating statistics for a numeric AliExpress product id. AliExpress currently returns up to 20 review records per page.

aliexpress_search

Search AliExpress products. Returns one page (up to 60 products) of public keyword search results with product ids, titles, links, images, prices, ratings, sold text, discount, SKU id, ship-from country, and store name when AliExpress lists them. Results can be sorted and filtered by price, free shipping, the Choice program, and product attributes; list the attribute values for a keyword with the search-filters endpoint. The search uses the anonymous US English/USD locale. Product-detail pages are currently unavailable through the supported HTTP profiles.

aliexpress_search_filters

List AliExpress search filters. Returns every sort value and boolean filter the search endpoint accepts, plus the product-attribute filters (brand, color, style, and so on) AliExpress offers for the keyword, as ready-to-use attr values. Attribute filters differ per keyword, so call this with the same q as the search.

aljazeera_article

Get Al Jazeera article content. Returns a public Al Jazeera article's metadata and body paragraphs from a canonical article URL.

aljazeera_author

Get an Al Jazeera author's profile and recent articles. Returns one Al Jazeera author's public profile (name, job title, bio when available) and one page of their recent articles, identified by an author slug or a canonical author URL.

aljazeera_categories

Get Al Jazeera section navigation. Returns Al Jazeera's current public section navigation. Use a returned slug directly as the topic parameter on aljazeera-topic.

aljazeera_headlines

Get Al Jazeera site-wide headlines. Returns fresh headlines from Al Jazeera's public, site-wide RSS feed.

aljazeera_topic

Get Al Jazeera section headlines. Returns the newest public Al Jazeera stories from one section archive page. topic is a section slug; use aljazeera-categories for the current value space.

allbirds_collection_products

List Allbirds collection products. Returns normalized products from one Allbirds (https://www.allbirds.com) collection. The storefront URL is fixed server-side; 'handle' is the collection's URL slug.

allbirds_collections

List Allbirds collections. Returns normalized collections from Allbirds (https://www.allbirds.com). The storefront URL is fixed server-side. Valid empty result pages return '200' with an empty collections array.

allbirds_page