Provides a tool to convert any web URL into clean Markdown, facilitating easier content processing and analysis by LLMs.
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.
npx searchclaw-mcpOr install globally:
npm install -g searchclaw-mcpRelated MCP server: MCP Server Metasearch
Get your API key from searchclaw.dev and add the server to your MCP client config.
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 mcp add searchclaw -- npx -y searchclaw-mcpThen set your API key in your environment:
export SEARCHCLAW_API_KEY="your-api-key"Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"searchclaw": {
"command": "npx",
"args": ["-y", "searchclaw-mcp"],
"env": {
"SEARCHCLAW_API_KEY": "your-api-key"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"searchclaw": {
"command": "npx",
"args": ["-y", "searchclaw-mcp"],
"env": {
"SEARCHCLAW_API_KEY": "your-api-key"
}
}
}
}Tool | Description | Credits |
| Web search — organic results | 1 |
| RAG-ready search with context and sources (primary tool for AI agents) | 2 |
| Search recent news articles | 1 |
| Search for images with metadata | 1 |
| Autocomplete / query suggestions | 1 |
Tool | Description | Credits |
| Extract structured data from a URL using a JSON schema | 5 |
| Convert any URL to clean markdown | 2 |
| Capture a full-page screenshot of a URL | 2 |
Tool | Description | Credits |
| Async bulk crawl with optional structured extraction | 1/page |
| Check status of an async crawl job | 0 |
| Discover all URLs on a domain (sitemap alternative) | 2 |
Tool | Description | Credits |
| Search + extract in one call — the killer feature for RAG pipelines | 3+ |
| Interactive browser actions (click, type, scroll) | 5 |
| Autonomous data gathering from natural language prompts | variable |
Tool | Description | Credits |
| Check your remaining API credits | 0 |
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.
MIT
Autonomous data gathering agent. Describe what you need in natural language and the agent will search, browse, and extract data. Costs variable credits.
Inputs: prompt (required), schema, max_credits, max_sources.
Interactive browser actions on a URL. Perform clicks, form fills, scrolling, and more. Costs 5 credits.
Inputs: url (required), actions (required).
Start an async bulk crawl with optional extraction. Returns a job ID to poll with job_status. Costs 1 credit per page.
Inputs: url (required), max_pages, schema.
Extract structured data from a URL using a JSON schema. Costs 5 credits.
Inputs: url (required), schema, prompt.
Search for images using SearchClaw. Returns image URLs and metadata. Costs 1 credit.
Inputs: q (required).
Check the status of an async job (e.g. crawl). Costs 0 credits.
Inputs: job_id (required).
Discover all URLs on a domain. Returns a sitemap-like list. Costs 2 credits.
Inputs: url (required), max_pages, search.
Convert a URL to clean markdown. Costs 2 credits.
Inputs: url (required).
Search for recent news articles using SearchClaw. Costs 1 credit.
Inputs: q (required).
Search + extract in one call. The killer feature — find pages via search, then extract structured data from top results. Costs 3+ credits.
Inputs: query (required), schema (required), max_results, extract_from.
Capture a screenshot of a URL. Costs 2 credits.
Inputs: url (required), full_page.
Search the web using SearchClaw. Returns organic web results. Costs 1 credit.
Inputs: q (required).
RAG-ready web search with context and sources. Primary tool for AI agents — returns structured context optimized for LLM consumption. Costs 2 credits.
Inputs: q (required).
Get autocomplete suggestions for a search query using SearchClaw. Costs 1 credit.
Inputs: q (required).
Check your SearchClaw API credit balance. Costs 0 credits.
Inputs: no named parameters.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 15 tools
Most tools have distinct purposes (e.g., search, crawl, extract, screenshot), but there is some overlap between 'search' and 'search_ai' (both perform web searches) and 'extract' and 'pipeline' (both extract structured data). Descriptions help differentiate them, but an agent might occasionally misselect between these pairs.
Tool names are mostly consistent, using lowercase snake_case throughout (e.g., 'job_status', 'search_ai'). However, there is one deviation: 'agent' is a single word while others follow a verb_noun or noun pattern. This minor inconsistency does not significantly hinder readability.
With 15 tools, the count is well-scoped for a web search and data extraction server. Each tool serves a clear purpose, such as browsing, crawling, extracting, and checking usage, without feeling bloated or insufficient for the domain.
The tool set provides comprehensive coverage for web search and data extraction tasks, including search variants (search, search_ai, news, images), data gathering (crawl, map), extraction (extract, pipeline, markdown), browser interaction (browse, screenshot), job management (job_status), and utility (suggest, usage). No obvious gaps exist for the server's purpose.
Web search API and MCP server for developers building AI agents.
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Web scraping, extraction and search for AI agents. Hosted MCP with workspace API keys.
Unified 15-tool SEO, SERP, clean Markdown & GEO (LLM citation Share-of-Voice) MCP server.
