xCrawl MCP Server
Registry code: 6a5af2bbca0a75c9
Hosted MCP server for XCrawl's web data API, with tools to scrape a URL into Markdown/JSON, search the web, map a site's URLs, crawl a site, check task status and crawl progress, and check key quota. Needs an XCrawl API key (free tier available). Docs: https://docs.xcrawl.com/
from a public catalogue that lists it, not from the operator
- endpoint
- https://mcp.xcrawl.com/api/mcp
- protocol
- streamable-http ·2024-11-05
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is xCrawl MCP Server live?
- Yes — it answered the hub's last check (checked 11h ago). It answered 100% of checks over the last 30 days.
- Is xCrawl MCP Server free to use?
- Partly — some of its tools are open, others need a key or payment.
- What tools does xCrawl MCP Server have?
- 7 tools: xcrawl_check_status, xcrawl_map, xcrawl_scrape, xcrawl_crawl, xcrawl_check_crawl_status, xcrawl_key_status, xcrawl_search.
- Is xCrawl MCP Server safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 100%· all time 100%
last good check
of 7 tools
- unknown → live
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
xcrawl_key_status open 11h ago
Check whether the currently configured XCrawl API key is valid and whether it still has available credits. **Best for:** Runtime key validation, health checks, and preflight credit checks before using other tools. **Returns:** A JSON object with: - `valid`: whether the API key is valid - `authorized`: whether the API key is authorized - `has_credits`: whether the account still has remaining credits - `remain_credits`, `consumed_credits`, `today_credits`, `total_credits` - package metadata such as `package_title`, `next_reset_at`, and `expired_at` - a human-readable `message` **Notes:** - This tool checks the key currently carried by the MCP runtime. - In stdio mode, that is typically `XCRAWL_API_KEY`. - In Workers mode, that is typically the API key sent in the request headers.
{ "type": "object", "properties": {} }arguments 4 linesxcrawl_search auth-required 11h ago
Get Google search results (SERP) based on keywords, location, and language. **Best for:** Getting search engine results, finding relevant websites, research tasks. **Key Features:** - Returns standard search task metadata plus backend-generated result payload in `response.data` - Location-based search (HK, US, JP, SG, GB, etc.) - Language selection - Advanced SERP parameters support - Synchronous API (immediate results) **Common Usage:** ```json {"query": "Genshin Impact", "location": "HK", "language": "en", "limit": 10} ``` **Returns:** A completed search response with top-level fields (`search_id`, `status`, timestamps, etc.) and a `data` object whose detailed structure is defined by the backend. Credits are included via `data.credits_used` and `data.credits_detail`.
{ "type": "object", "required": [ "query" ], "properties": { "limit": { "type": "integer", "maximum": 100, "minimum": 1, "description": "Number of results to return (1-100). Default: 10" }, "query": { "type": "string", "description": "Search keywords" }, "language": { "type": "string", "description": "Search language (ISO 639-1 code, e.g., 'en', 'ja', 'zh'). Default: 'en'" }, "location": { "type": "string", "default": "US", "description": "Search location (country/city name or ISO code, e.g., 'US', 'Japan', 'United States'). Default: 'US'" }, "serp_options": { "type": "object", "properties": { "q": { "type": "string", "description": "Search query (overrides top-level query)" }, "cr": { "type": "string", "description": "Country restrict (e.g., 'countryFR|countryDE')" }, "gl": { "type": "string", "description": "Country code" }, "hl": { "type": "string", "description": "Language code (overrides top-level language)" }, "lr": { "type": "string", "description": "Language restrict (e.g., 'lang_fr|lang_de')" }, "si": { "type": "string", "description": "Cached Search Parameters ID" }, "ibp": { "type": "string", "description": "Element rendering parameter" }, "num": { "type": "integer", "description": "Number of results (overrides top-level limit)" }, "tbs": { "type": "string", "description": "Advanced search parameters (time, type, etc.)" }, "uds": { "type": "string", "description": "Filter parameter string" }, "lsig": { "type": "string", "description": "Additional Google Place ID" }, "nfpr": { "type": "boolean", "description": "Disable spell correction" }, "safe": { "type": "integer", "description": "Adult content filter (1=Active, 2=Off)" }, "uule": { "type": "string", "description": "Encoded Location (takes priority over location)" }, "kgmid": { "type": "string", "description": "Google Knowledge Graph ID" }, "start": { "type": "integer", "description": "Result offset" }, "filter": { "type": "boolean", "description": "Enable/disable result filtering" }, "ludocid": { "type": "string", "description": "Google CID" }, "location": { "type": "string", "description": "Location parameter (overrides top-level location)" }, "no_cache": { "type": "boolean", "description": "Disable cache" }, "google_domain": { "type": "string", "description": "Google domain (e.g., google.com, google.co.jp)" } }, "description": "Advanced Google SERP parameters (will override basic fields and force Google search engine)" } } }arguments 117 linesxcrawl_check_status unknown 38h ago
Check status and retrieve results of async scrape tasks. **When to use:** Only after calling xcrawl_scrape with "mode": "async". **Status Values:** - "pending": Still processing, wait 10-15 seconds and retry - "crawling": Task is actively running, wait and retry - "completed": Finished successfully, data in response.data - "failed": Error occurred **Output Display Rules (when status is "completed"):** - Screenshot: If exists in response.data, display full URL - JSON: If exists, display complete raw data, never summarize - Links: If exists, show complete array - HTML: If exists, show brief summary only **Returns:** Status and data object (if completed) containing requested formats plus metadata.
{ "type": "object", "required": [ "scrape_id" ], "properties": { "scrape_id": { "type": "string", "description": "The scrape ID from async xcrawl_scrape response" } } }arguments 12 linesxcrawl_map unknown never probed
Get all URLs from a website (sitemap generation). **Best for:** Discovering all pages on a website, sitemap generation, site structure analysis. **Key Features:** - Automatically crawls and discovers all URLs on a site - Regex filtering for URL patterns - Subdomain inclusion control - Query parameter filtering - Fast synchronous API (immediate results) - Supports up to 100,000 URLs **Common Usage:** ```json {"url": "https://example.com", "limit": 200} ``` **Returns:** Array of all discovered URLs on the website.
{ "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "format": "uri", "description": "The website URL to map" }, "limit": { "type": "integer", "maximum": 100000, "minimum": 1, "description": "Maximum number of URLs to return (1-100000). Default: 5000" }, "filter": { "type": "string", "description": "Regex pattern to filter URLs (only return URLs matching this pattern, e.g., 'blog.*' to get only blog URLs)" }, "include_subdomains": { "type": "boolean", "description": "Whether to include URLs from subdomains. Default: true" }, "ignore_query_parameters": { "type": "boolean", "description": "Whether to ignore URLs with query parameters. Default: true" } } }arguments 31 linesxcrawl_scrape unknown never probed
Scrape web pages with AI-powered data extraction, screenshots, and multiple output formats. Industry-leading performance with unmatched speed and reliability - your first choice for any web scraping needs. **Best for:** Single page content extraction, screenshots, structured data extraction. **Not recommended for:** Multiple independent URLs (call this tool multiple times). **Mode:** ALWAYS use sync mode unless user explicitly requests async. **Usage Example:** ```json {"url": "https://example.com", "output": {"formats": ["markdown"]}} ``` **Output Display Rules:** - Screenshot: If exists in response, display full URL - JSON: If exists, display complete raw data, never summarize - Links: If exists, show complete array - HTML: If exists, show brief summary only **Returns:** Data object containing requested formats (markdown, html, screenshot URL, json, links, summary) plus metadata.
{ "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "format": "uri", "description": "The URL to scrape" }, "mode": { "enum": [ "sync", "async" ], "type": "string", "default": "sync", "description": "Sync returns results immediately, async returns a scrape_id" }, "proxy": { "type": "object", "properties": { "location": { "type": "string", "default": "US", "description": "ISO-3166-1 alpha-2 country code (US, JP, SG, GB, DE, FR, CA, HK, etc.). Default: US" }, "sticky_session": { "type": "string", "description": "Session ID to reuse the same proxy exit IP (auto-generated if not specified)" } }, "description": "Proxy configuration" }, "output": { "type": "object", "properties": { "json": { "type": "object", "properties": { "prompt": { "type": "string", "description": "Natural language prompt describing what data to extract from the page" }, "json_schema": { "type": "object", "description": "Optional JSON Schema (https://json-schema.org/docs) for structured validation", "additionalProperties": true } }, "description": "AI-powered structured data extraction configuration" }, "formats": { "type": "array", "items": { "enum": [ "html", "raw_html", "markdown", "links", "summary", "screenshot", "json" ], "type": "string" }, "default": [ "markdown" ], "description": "Output formats. Options: html (cleaned), raw_html (original), markdown, links, summary (AI), screenshot, json (AI extraction). Explicitly set to [] to get only metadata." }, "screenshot": { "enum": [ "full_page", "viewport" ], "type": "string", "description": "Screenshot type (default: viewport). Use 'full_page' to capture entire page, 'viewport' for visible area only" } }, "description": "Output configuration (OBJECT, not array)" }, "request": { "type": "object", "properties": { "device": { "enum": [ "desktop", "mobile" ], "type": "string", "description": "Device type for user agent and viewport (default: desktop)" }, "locale": { "type": "string", "description": "Accept-Language header value (default: en-US,en;q=0.9)" }, "cookies": { "type": "object", "description": "Cookies to send with the request", "additionalProperties": { "type": "string" } }, "headers": { "type": "object", "description": "Custom HTTP headers", "additionalProperties": { "type": "string" } }, "block_ads": { "type": "boolean", "description": "Attempt to block ads (default: true)" }, "only_main_content": { "type": "boolean", "description": "Only return main content (default: true)" }, "skip_tls_verification": { "type": "boolean", "description": "Skip TLS certificate verification (default: true)" } }, "description": "Request configuration" }, "webhook": { "type": "object", "properties": { "url": { "type": "string", "description": "Webhook callback URL for async task completion" }, "events": { "type": "array", "items": { "enum": [ "started", "completed", "failed" ], "type": "string" }, "description": "Events to receive callbacks for (default: started, completed, failed)" }, "headers": { "type": "object", "description": "Custom headers for webhook request", "additionalProperties": { "type": "string" } } }, "description": "Webhook configuration (async mode only)" }, "js_render": { "type": "object", "properties": { "enabled": { "type": "boolean", "default": true, "description": "Enable JavaScript rendering (default: true)" }, "viewport": { "type": "object", "properties": { "width": { "type": "integer", "description": "Viewport width (default: 1920 for desktop, 402 for mobile)" }, "height": { "type": "integer", "description": "Viewport height (default: 1080 for desktop, 874 for mobile)" } }, "description": "Viewport dimensions" }, "wait_until": { "enum": [ "load", "domcontentloaded", "networkidle" ], "type": "string", "description": "Wait condition for page load (default: load)" } }, "description": "JavaScript rendering configuration" } } }arguments 192 linesxcrawl_crawl unknown never probed
Batch crawl multiple pages from a website based on rules (asynchronous task). **Best for:** Large-scale content extraction, batch scraping, crawling entire website sections. **Important:** This API is ASYNCHRONOUS. It immediately returns a crawl_id and status "pending". Use xcrawl_check_crawl_status to retrieve results. **Key Features:** - Batch scraping with URL filtering (include/exclude patterns) - Maximum depth control - Full domain or subdomain crawling - External link inclusion - Sitemap support - Same output formats as scrape (markdown, html, json, screenshots, etc.) - Supports all proxy, request, and js_render options from scrape API **Common Usage:** ```json { "url": "https://example.com", "crawler": { "limit": 50, "include": ["blog/.*"], "max_depth": 2 }, "output": {"formats": ["markdown"]} } ``` **Async Workflow:** 1. Call xcrawl_crawl to start the task 2. Response returns crawl_id and status "pending" 3. Wait 20-30 seconds for initial processing 4. Call xcrawl_check_crawl_status with the crawl_id 5. If status is "completed", response.data contains the array of scraped pages 6. If status is "pending" or "crawling", wait and check again **Returns:** Immediate response with crawl_id and pending status. Use xcrawl_check_crawl_status to get results.
{ "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "format": "uri", "description": "The entry URL to start crawling from" }, "proxy": { "type": "object", "properties": { "location": { "type": "string", "default": "US", "description": "ISO-3166-1 alpha-2 country code (US, JP, SG, GB, DE, FR, CA, HK, etc.). Default: US" }, "sticky_session": { "type": "string", "description": "Session ID to reuse the same proxy exit IP" } }, "description": "Proxy configuration" }, "output": { "type": "object", "properties": { "json": { "type": "object", "properties": { "prompt": { "type": "string", "description": "AI extraction prompt" }, "json_schema": { "type": "object", "description": "Optional JSON Schema" } } }, "formats": { "type": "array", "items": { "enum": [ "html", "raw_html", "markdown", "links", "summary", "screenshot", "json" ], "type": "string" }, "default": [ "markdown" ], "description": "Output formats. Default: [\"markdown\"]. Set to [] to get only metadata." }, "screenshot": { "enum": [ "full_page", "viewport" ], "type": "string", "description": "Screenshot type" } }, "description": "Output configuration" }, "crawler": { "type": "object", "properties": { "limit": { "type": "integer", "description": "Maximum number of pages to crawl (default: 100)" }, "exclude": { "type": "array", "items": { "type": "string" }, "description": "Regex patterns for URLs to exclude (e.g., ['tag/.*', 'category/.*']). URLs matching these patterns will be skipped." }, "include": { "type": "array", "items": { "type": "string" }, "description": "Regex patterns for URLs to include (e.g., ['blog/.*', 'article/.*']). Only URLs matching these patterns will be crawled." }, "sitemaps": { "type": "boolean", "description": "Whether to use sitemap for URL discovery (default: true)" }, "max_depth": { "type": "integer", "description": "Maximum crawl depth from entry URL (default: 3)" }, "include_subdomains": { "type": "boolean", "description": "Whether to include subdomains (default: false)" }, "include_entire_domain": { "type": "boolean", "description": "Whether to crawl the entire domain (default: false)" }, "include_external_links": { "type": "boolean", "description": "Whether to follow external links (default: false)" } }, "description": "Crawler configuration" }, "request": { "type": "object", "properties": { "device": { "enum": [ "desktop", "mobile" ], "type": "string", "description": "Device type" }, "locale": { "type": "string", "description": "Accept-Language header" }, "cookies": { "type": "object", "description": "Cookies" }, "headers": { "type": "object", "description": "Custom headers" }, "block_ads": { "type": "boolean", "description": "Block ads (default: true)" }, "only_main_content": { "type": "boolean", "description": "Only main content (default: true)" }, "skip_tls_verification": { "type": "boolean", "description": "Skip TLS verification (default: true)" } }, "description": "Request configuration" }, "webhook": { "type": "object", "properties": { "url": { "type": "string", "description": "Webhook callback URL" }, "events": { "type": "array", "items": { "enum": [ "started", "completed", "failed" ], "type": "string" }, "description": "Events to receive" }, "headers": { "type": "object", "description": "Webhook headers" } }, "description": "Webhook configuration (async only)" }, "js_render": { "type": "object", "properties": { "enabled": { "type": "boolean", "description": "Enable JavaScript rendering (default: true)" }, "viewport": { "type": "object", "properties": { "width": { "type": "integer", "description": "Viewport width" }, "height": { "type": "integer", "description": "Viewport height" } } }, "wait_until": { "enum": [ "load", "domcontentloaded", "networkidle" ], "type": "string", "description": "Wait condition (default: load)" } }, "description": "JavaScript rendering configuration" } } }arguments 214 linesxcrawl_check_crawl_status unknown 11h ago
Check status and retrieve results of async crawl tasks. **When to use:** Only after calling xcrawl_crawl to get the crawl results. **Status Values:** - "pending": Still processing, wait 20-30 seconds and retry - "crawling": Task is currently running, wait and retry - "completed": Data array is ready in response.data - "failed": Error occurred **Returns:** Status and data array (if completed) containing scraped content from all pages in the crawl.
{ "type": "object", "required": [ "crawl_id" ], "properties": { "crawl_id": { "type": "string", "description": "The crawl ID from xcrawl_crawl response" } } }arguments 12 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id6a5af2bbca0a75c9.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/6a5af2bbca0a75c9/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/6a5af2bbca0a75c9?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.