Productivity · Local MCP server

TheCrawler

Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.manchittlab/thecrawler
Version
0.5.8
Status
Active
Category
productivity
Transport
stdio (local process)
Package
npm
Published
2026-07-02
Updated
2026-07-02
Publisher
manchittlab (GitHub)
Listed under
PDF MCP servers
Repository
github.com/manchittlab/TheCrawler
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npmthecrawler0.5.8stdioNone declared

How to connect TheCrawler

TheCrawler runs locally from a Node.js package published to the npm registry: thecrawler version 0.5.8. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y thecrawler@0.5.8.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "thecrawler": {
      "command": "npx",
      "args": [
        "-y",
        "thecrawler@0.5.8"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More productivity servers

All 3,040 →
ServerRunsEndpoint or package
The Service Marketing Guys AuditRead-only audit of any local service business, Open Service Profile conformance first.Remote · HTTPtheservicemarketingguys.com
The WireA public meeting place for agents to exchange reviews and coordinate work.Remote · HTTPthe-wire.qualium.workers.dev
The-SnipTeam knowledge base for snippets, API calls and docs. Agents search and file items; humans review.Remote · HTTPthe-snip.com
TheBetterHireAI screening interviews, resume matching, and evidence-linked scorecards for recruiting teams.Remote · HTTPmcp.thebetterhire.ai
TheQRCode.ioFree styled QR codes, no key: URL, WiFi, contact, text, email. API key adds saved codes + analytics.Remote · HTTPmcp.theqrcode.io
ThesportsdbTheSportsDB MCP — sports catalog (teams, players, events)Remote · HTTPgateway.pipeworx.io
thinqOSMemory with judgment: decides which of your context reaches each task, per identity.Remote · HTTPapp.thinqos.com
ThoughtboxExtended reasoning with structured processes, persistence, and workflow guidance.Local · stdionpm: @kastalien-research/thoughtbox