Skip to main content
Glama
Fast Website RAG Markdown Crawler & B2B Contact Finder MCP Server

Fast Website RAG Markdown Crawler & B2B Contact Finder MCP Server

by willowswt

crawl_website_to_rag_markdown

Read-onlyIdempotent

Crawl websites or sitemaps into clean, LLM-ready Markdown and token-bounded RAG chunks without headless browser overhead, preparing site content for retrieval-augmented generation pipelines.

Instructions

Crawl any website or sitemap into clean LLM-ready Markdown and token-bounded RAG chunks without headless browser overhead.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "startUrls": "<startUrls>"
    },
    "name": "crawl_website_to_rag_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
startUrlsYesList of URLs or bare domains to crawl.
useSitemapNoDiscover internal pages via /sitemap.xml.
chunkSizeWordsNoTarget word count per RAG chunk.
maxPagesPerSiteNoMax pages to extract per starting domain.
includeRagChunksNoSplit Markdown into token-bounded RAG chunks.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds a genuine behavioral hint — no headless browser, implying static HTML crawling with limited JS rendering — but leaves it ambiguous, and says nothing about rate limits, robots.txt handling, or failure behavior on unreachable pages.

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?

A single front-loaded sentence with no structural waste; the core verb and output shape lead. The marketing-flavored modifiers ('clean LLM-ready', 'without headless browser overhead') are the only padding, and the latter at least hints at behavior.

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

Completeness3/5

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

For a 5-parameter crawl tool with no output schema, describing the return shape as Markdown plus RAG chunks is valuable. However, it omits scope controls (how deep/large a crawl can get), what happens with JS-heavy or blocked sites, and how sitemap discovery interacts with the other options, leaving real gaps for a tool that hits arbitrary external sites.

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

Parameters3/5

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

Schema description coverage is 100%, with per-parameter descriptions for startUrls, useSitemap, chunkSizeWords, maxPagesPerSite and includeRagChunks, so the schema does the heavy lifting. The description adds no meaning beyond that — it never mentions chunk sizing, page caps, or the sitemap toggle, so the baseline 3 applies.

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

Purpose4/5

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

The description pairs a specific verb (crawl) with concrete resources (website or sitemap) and names both output artifacts (Markdown and token-bounded RAG chunks), so an agent knows exactly what it produces. It does not differentiate itself from the only sibling (find_company_emails_phones_tech), though that omission is minor given the clearly unrelated domain.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, no prerequisites, and no named alternatives. The phrase 'without headless browser overhead' gestures at a comparison but never states the condition under which that trade-off matters (e.g. JS-rendered sites).

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