Webclaw MCP Server

<strong>Turn websites into clean markdown, JSON, and LLM-ready context.</strong>

Remote serverstreamable-httpPython

What is the Webclaw MCP server?

Turn websites into clean markdown, JSON, and LLM-ready context.. Exposed over MCP by the webclaw mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • scrape — Extract one URL as markdown, text, JSON, LLM format, or HTML
  • crawl — Follow same-origin links and extract discovered pages
  • map — Discover URLs without extracting every page
  • batch — Scrape multiple URLs in parallel
  • extract — Convert page content into structured data
  • summarize — Summarize a page
  • diff — Compare page content snapshots
  • brand — Extract colors, fonts, logos, and metadata
  • search — Search the web and scrape results
  • research — Multi-source research workflow
  • Homebrew — The Homebrew tool exposed by this server
  • Cargo — If building from source fails because native build tools are missing, install the platform prerequisites:

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 6 environment variables: WEBCLAW_API_KEY, OLLAMA_HOST, OPENAI_API_KEY, OPENAI_BASE_URL, ANTHROPIC_API_KEY, ANTHROPIC_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Webclaw's toolset — scrape, crawl, map and 9 more — is a fair guide to whether it matches your workflow. It is maintained by 0xmassi; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Webclaw's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Webclaw.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the webclaw mcp server does with a few real requests.

Available tools

ToolWhat it does
scrapeExtract one URL as markdown, text, JSON, LLM format, or HTML
crawlFollow same-origin links and extract discovered pages
mapDiscover URLs without extracting every page
batchScrape multiple URLs in parallel
extractConvert page content into structured data
summarizeSummarize a page
diffCompare page content snapshots
brandExtract colors, fonts, logos, and metadata
searchSearch the web and scrape results
researchMulti-source research workflow
HomebrewThe Homebrew tool exposed by this server.
CargoIf building from source fails because native build tools are missing, install the platform prerequisites:

How to install the Webclaw MCP server

{
  "mcpServers": {
    "webclaw": {
      "command": "npx",
      "args": ["-y", "@webclaw/mcp"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
WEBCLAW_API_KEYCredential the server authenticates with.Yes
OLLAMA_HOSTEndpoint or connection string the server talks to.Optional
OPENAI_API_KEYCredential the server authenticates with.Yes
OPENAI_BASE_URLEndpoint or connection string the server talks to.Yes
ANTHROPIC_API_KEYCredential the server authenticates with.Yes
ANTHROPIC_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Webclaw to scrape.
  • Use Webclaw to crawl.
  • Use Webclaw to map.

Frequently asked questions

It connects Webclaw to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (scrape, crawl, map, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Webclaw directly.