SearchClaw MCP Server

The complete web data pipeline for AI agents — Search, Extract, Crawl in One API.

README.md

SearchClaw MCP Server

The complete web data pipeline for AI agents. Search, Extract, Crawl in One API.

A Model Context Protocol (MCP) server with 15 tools covering web search, scraping, extraction, crawling, and autonomous data gathering via the SearchClaw API.

Installation

npx searchclaw-mcp

Or install globally:

npm install -g searchclaw-mcp

Configuration

Get your API key from searchclaw.dev and add the server to your MCP client config.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "searchclaw": {
      "command": "npx",
      "args": ["-y", "searchclaw-mcp"],
      "env": {
        "SEARCHCLAW_API_KEY": "your-api-key"
      }
    }
  }
}

Claude Code

claude mcp add searchclaw -- npx -y searchclaw-mcp

Then set your API key in your environment:

export SEARCHCLAW_API_KEY="your-api-key"

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "searchclaw": {
      "command": "npx",
      "args": ["-y", "searchclaw-mcp"],
      "env": {
        "SEARCHCLAW_API_KEY": "your-api-key"
      }
    }
  }
}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "searchclaw": {
      "command": "npx",
      "args": ["-y", "searchclaw-mcp"],
      "env": {
        "SEARCHCLAW_API_KEY": "your-api-key"
      }
    }
  }
}

Available Tools (15)

Search

Tool Description Credits
search Web search — organic results 1
search_ai RAG-ready search with context and sources (primary tool for AI agents) 2
news Search recent news articles 1
images Search for images with metadata 1
suggest Autocomplete / query suggestions 1

Extract & Scrape

Tool Description Credits
extract Extract structured data from a URL using a JSON schema 5
markdown Convert any URL to clean markdown 2
screenshot Capture a full-page screenshot of a URL 2

Crawl

Tool Description Credits
crawl Async bulk crawl with optional structured extraction 1/page
job_status Check status of an async crawl job 0
map Discover all URLs on a domain (sitemap alternative) 2

Pipeline & Agents

Tool Description Credits
pipeline Search + extract in one call — the killer feature for RAG pipelines 3+
browse Interactive browser actions (click, type, scroll) 5
agent Autonomous data gathering from natural language prompts variable

Utility

Tool Description Credits
usage Check your remaining API credits 0

Why SearchClaw?

Feature SearchClaw Firecrawl Tavily
Web search
AI search (RAG)
Extract with schema
Crawl
Pipeline (search + extract)
Autonomous agent
Browser actions
News & image search
Screenshot
MCP server
Free tier ✅ 500 credits/mo ✅ 1000 credits/mo

Get started at searchclaw.dev.

License

MIT

Tools 15

searchPerform an organic web search.
search_aiRAG-ready search with context and sources.
newsSearch for recent news articles.
imagesSearch for images with metadata.
suggestGet autocomplete or query suggestions.
extractExtract structured data from a URL using a JSON schema.
markdownConvert any URL to clean markdown.
screenshotCapture a full-page screenshot of a URL.
crawlPerform async bulk crawl with optional structured extraction.
job_statusCheck the status of an async crawl job.
mapDiscover all URLs on a domain.
pipelinePerform search and extraction in one call.
browsePerform interactive browser actions like click, type, and scroll.
agentAutonomous data gathering from natural language prompts.
usageCheck remaining API credits.

Environment Variables

SEARCHCLAW_API_KEYrequiredAPI key obtained from searchclaw.dev

Try it

Search for the latest news on AI regulations and summarize the key points.
Extract the product pricing and features from this URL into a JSON format: [URL]
Crawl the documentation site at [URL] and convert the pages to markdown.
Use the autonomous agent to research the current market competitors for a new SaaS product.
Take a screenshot of the landing page at [URL] and describe the visual layout.

Frequently Asked Questions

What are the key features of SearchClaw?

Integrated web search and RAG-ready AI search. Structured data extraction from URLs using JSON schemas. Async bulk crawling and domain mapping capabilities. Autonomous data gathering agents. Interactive browser actions including clicking and typing.

What can I use SearchClaw for?

Building RAG pipelines that require real-time web data. Automating competitive research and market analysis. Converting complex web pages into clean markdown for LLM context. Monitoring news and updates across multiple domains. Automated testing of web interfaces via browser actions.

How do I install SearchClaw?

Install SearchClaw by running: npx searchclaw-mcp

What MCP clients work with SearchClaw?

SearchClaw works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep SearchClaw docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Open Conare