Skip to main content
Glama
RapierCraft

alterlab-mcp-server

by RapierCraft

alterlab_crawl

Crawl entire websites for RAG or indexing, automatically bypassing anti-bot protection. Returns markdown, text, or structured data with a crawl ID for polling.

Instructions

Crawl an entire website for RAG, index all pages on a site, or build a knowledge base from a domain. Automatically bypasses anti-bot protection on every page — works on Cloudflare-protected sites. Discovers URLs via sitemap parsing and link extraction, then scrapes each page asynchronously. Returns content as clean markdown, text, or structured data. Returns a crawl_id immediately — use alterlab_crawl_status to poll results. Use include_patterns/exclude_patterns to scope the crawl to specific sections. Use render_js='auto' for mixed sites to save 30-60% vs always rendering. Supports extraction_schema or extraction_profile to extract structured data from every page. Use cost_controls to cap total credits or pin the scraping tier for all pages. Use sitemap_path to specify a non-standard sitemap location. Use headers to inject custom HTTP headers (e.g., Authorization) into every page request.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesStart URL for the crawl
formatsNoOutput formats for each scraped page
headersNoCustom HTTP headers injected into every page request during the crawl (e.g., {"Authorization": "Bearer token"}). Maximum 50 headers.
sitemapNoSitemap mode: include (default), skip (link extraction only), only (sitemap URLs only)include
timeoutNoPer-page request timeout in seconds (1-300)
wait_forNoCSS selector to wait for before extracting each page (e.g., '#main-content'). Applied to all pages in the crawl.
max_depthNoMaximum link-following depth from start URL (0 = start page only)
max_pagesNoMaximum number of pages to scrape
render_jsNoRender JavaScript on crawled pages. true=always (Tier 4), false=never, auto=smart detection per page
use_proxyNoRoute all crawl requests through premium proxy
webhook_urlNoWebhook URL to notify on crawl completion
block_imagesNoBlock image downloads during browser rendering on each crawled page. Reduces proxy bandwidth and speeds up crawls. Only effective with render_js=true.
sitemap_pathNoExplicit path to the sitemap file (e.g., '/sitemap_index.xml'). Use when the sitemap is not at the standard /sitemap.xml location.
cost_controlsNoCost controls for the entire crawl — cap total spend or pin the scraping tier
respect_robotsNoRespect robots.txt rules for the target domain
max_concurrencyNoMaximum concurrent pages to scrape simultaneously
exclude_patternsNoGlob patterns — skip URLs whose path matches any (e.g., ['/tag/*', '/author/*'])
extraction_modelNoPer-request LLM model override in provider-specific format (e.g. 'gpt-4o', 'claude-opus-4-5-20251101', 'llama3-70b-8192'). Overrides the model saved in your BYOK key settings for this request only.
include_patternsNoGlob patterns — only scrape URLs whose path matches at least one (e.g., ['/blog/*', '/docs/*'])
extraction_schemaNoJSON schema for structured extraction on each page
extraction_profileNoPre-defined extraction profile applied to every crawled page. 'auto' detects the page type automatically.
include_subdomainsNoInclude links to subdomains during discovery
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses key behaviors: auto-bypassing anti-bot protection (works on Cloudflare), URL discovery via sitemap and link extraction, asynchronous scraping, return of crawl_id for polling, and support for patterns, render_js options, and cost controls. Missing details on rate limits or error handling, but overall transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized for a complex tool, with each sentence adding meaningful information. It front-loads the main purpose and then lists features. Could be slightly improved with bullet points or clearer grouping, but it is well-structured and not verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 22 parameters, high schema coverage, and no output schema, the description is comprehensive. It covers major use cases, parameter interactions, and return behavior (crawl_id for polling). Minor gap: does not describe output format details beyond 'clean markdown, text, or structured data,' but sufficient for initial selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value beyond schema by explaining render_js='auto' savings, cost_controls for capping or pinning tiers, sitemap_path for non-standard locations, and headers for injection. This enriches understanding and usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Crawl an entire website for RAG, index all pages on a site, or build a knowledge base from a domain.' It uses specific verbs and resources, and distinguishes from siblings like alterlab_scrape (single page) by emphasizing full-site crawling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on when to use the tool (for site crawling, RAG, knowledge base), mentions polling with alterlab_crawl_status, and explains scoping patterns and cost controls. It implies alternatives (e.g., single scrapes via alterlab_scrape) but does not explicitly state when not to use or compare to siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RapierCraft/alterlab-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server