Skip to main content
Glama
Sign In
CrawlEngine MCP

CrawlEngine MCP

by johannschiffer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

crawlengine-mcp

PyPI version CI License: MIT Python 3.10+ MCP Compliant Awesome MCP Servers

CrawlEngine MCP is a Model Context Protocol (2024-11-05) web extraction server built on httpx and beautifulsoup4 that converts HTML pages into clean Markdown, resolves relative links, extracts JSON-LD and HTML tables, and rotates browser headers and HTTP/SOCKS5 proxies.

Listed in TensorBlock/awesome-mcp-servers.

Why CrawlEngine MCP?

  1. Context Window Efficiency: Strips <script>, <style>, <nav>, <footer>, cookie banners, and ads before returning Markdown to the model.

  2. Resolved Canonical Links: Converts relative <a href="/docs/start"> paths into full URLs using the page's base_url.

  3. Outbound SSRF Protection: Blocks loopback, RFC1918 private networks, and cloud metadata (169.254.169.254) on both initial requests and HTTP redirects.

Related MCP server: read-website-fast

Features

  • Semantic Markdown Extraction: Preserves headings, lists, code blocks, blockquotes, and resolved inline links without duplicating nested list paragraphs.

  • Browser Header Rotation: Rotates realistic Chrome, Firefox, and Safari User-Agent and Sec-Ch-Ua client-hint headers.

  • HTTP & SOCKS5 Proxy Pool: Round-robin rotation via CRAWLENGINE_PROXIES (httpx[socks]) with automatic ejection after 3 consecutive failures.

  • Structured Data & Metadata: Extracts application/ld+json schemas, HTML <table> rows, OpenGraph tags, canonical URLs, and filtered internal/external links.

Quickstart

Run with uvx

uvx crawlengine-mcp

Claude Desktop / Cursor Configuration

{
  "mcpServers": {
    "crawlengine-mcp": {
      "command": "uvx",
      "args": ["crawlengine-mcp"]
    }
  }
}

CLI Usage

crawlengine-cli scrape https://example.com
crawlengine-cli links https://example.com --internal-only
crawlengine-cli meta https://example.com

MCP Tools Available

Tool

Parameters

Description

scrape_url

url, extract_markdown, use_proxy, timeout

Fetch an HTTP(S) page and convert its main content into Markdown

extract_structured_data

url

Parse application/ld+json blocks and HTML tables into JSON records

extract_links

url, internal_only

Return deduplicated absolute hyperlinks with anchor text

extract_metadata

url

Extract page title, meta description, OpenGraph tags, and canonical URL

get_proxy_status

(none)

Inspect total, healthy, and ejected proxy counts in CRAWLENGINE_PROXIES

Genesis MCP Ecosystem

Module

Description

Repository

CrawlEngine MCP

HTTP web extraction to clean Markdown, JSON-LD parsing, and proxy rotation

GitHub

BrowserBridge MCP

Lightweight HTTP/DOM session automation with SHA-256 action receipts

GitHub

PgSafe MCP

Read-only PostgreSQL/SQLite query guard, PII masking, and dry-run mutations

GitHub

OmniBridge MCP

Multi-channel notification bus with SQLite retry queue

GitHub

SysFlow MCP

Linux systemd inspection, confined log tailing, and port auditing

GitHub

FastMCP Forge

Zero-dependency FastMCP framework, CLI scaffolder, and SSE middleware

GitHub

Support

If you find this project useful, you can support maintenance on Ko-fi.

License

MIT (c) 2026 Johann Schiffer

Available Tools

3 tools
extract_linksC

Extract all navigable hyperlinks, anchors, and references from a web page.

Inputs: url (required), internal_only.

extract_metadataB

Retrieve page title, OpenGraph tags, meta descriptions, and canonical links.

Inputs: url (required).

scrape_urlB

Scrape a web page with browser fingerprinting and convert its content into clean, token-efficient Markdown.

Inputs: url (required), timeout, extract_markdown.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct page-extraction concern: full content as Markdown, hyperlinks, and metadata. An agent can choose unambiguously based on the desired output.

    Naming Consistency5/5

    All names follow a verb_noun snake_case pattern (scrape_url, extract_links, extract_metadata). The two extract_* tools share a clear family, and the slight verb difference is semantically appropriate.

    Tool Count4/5

    Three tools is a lean but reasonable surface for a page-level scraping utility, and each tool earns its place. However, for a server branded as a 'CrawlEngine,' the count feels slightly under-scoped for crawling workflows.

    Completeness3/5

    The set covers single-page content, links, and metadata, but no tool actually crawls a site, follows extracted links, or handles batches/sitemaps. This is a notable gap for a crawl engine, though an agent could chain extract_links and scrape_url manually.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • cleanfetch

      belzorash
      A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to read web pages reliably, returning clean markdown content, hyperlinks, and metadata without navigation or ad noise.
      3
      5 npm
      MIT

    • read-website-fast

      Gomez89823
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents and LLM pipelines to fetch and crawl web pages, extract readable content, and convert it into clean Markdown with preserved links while minimizing token usage.
      MIT

    • read-website-fast

      Leonie64245
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to fetch and crawl web pages, strip noise, and convert content into clean Markdown with preserved links for token-efficient scraping and downstream processing.
      MIT