1. Conduid
  2. Browser
  3. Docs Crawler MCP
MCP server · Browser

Docs Crawler MCP

by · github.com/Yazington/docs-crawler-mcp

MCP server: Docs Crawler MCP

Unclaimed last commit a year ago browser
InstallView source
37Low

Scored 5 months ago · breakdown

About Docs Crawler MCP

Docs Crawler MCP is an MCP server published by Yazington in the Browser category: mCP server: Docs Crawler MCP.

The repository has 3 stars and 1 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/Yazington/docs-crawler-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Docs Crawler MCP

Powered by Claude · Grounded in docs

I know everything about Docs Crawler MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository yesterday. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Quasar Crawler MCP Server

An MCP server that crawls documentation websites, converts them to Markdown, and stores embeddings in Qdrant for intelligent, up-to-date documentation search.

Features

  • Crawl documentation sites using Puppeteer
  • Convert HTML to Markdown with jsdom and turndown
  • Generate embeddings with Transformers
  • Store and search embeddings in Qdrant vector database
  • Expose MCP resources and tools for integration with other systems

Installation

Clone the repository and install dependencies:

npm install

Build the project:

npm run build

Usage

Configure this server as an MCP server (e.g., in Claude Desktop configuration):

{
  "mcpServers": {
    "quasar-crawler": {
      "command": "/path/to/quasar-crawler/build/index.js"
    }
  }
}

Run the built server binary, then use the provided MCP tools and resources to crawl and query documentation content.

Development

For active development with auto-rebuild:

npm run watch

Available scripts:

  • build - Compile the TypeScript source
  • watch - Rebuild on file changes
  • inspector - Launch MCP Inspector for debugging

Debugging

Use the MCP Inspector to debug server communication:

npm run inspector

This will provide a URL to access debugging tools in your browser.

Dependencies

README fetched from the repository yesterday. The original is authoritative.

Questions

About Docs Crawler MCP

How do I install Docs Crawler MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Docs Crawler MCP safe to use with an AI agent?

Its trust score is 37 out of 100 (low). It passes 3 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Docs Crawler MCP still maintained?

The last commit was a year ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.