SearchMCP
Connect any LLM to the internet with the cheapest, most reliable, and developer-friendly search API.
@searchmcp/client
Thin TypeScript/JavaScript SDK for the SearchMCP API.
Generated from the OpenAPI spec using typescript-fetch.
Supports REST (/v1/search) endpoint.
Includes full type definitions out of the box.
Pre-Installation
Checkout
- 📚 SearchMCP Docs
- 🔎 SearchMCP API Reference
Installation
npm install @searchmcp/client
or
pnpm add @searchmcp/client
or
yarn add @searchmcp/client
Requires Node.js 18+ (native fetch).
Usage
import {createClient} from "@searchmcp/client";
const client = createClient(process.env.SEARCHMCP_API_KEY);
// Simple web search const res = await client.search({ query: "latest GPU deals", country: "US", numberOfResults: 5, });
console.log(res.status); // "SUCCESS" console.log(res.results); // array of results
Client Factory
import {createClient, SearchMCPClient} from "@searchmcp/client";
const client: SearchMCPClient = createClient("smcp_123", "https://api.searchmcp.io");
apiKey— requiredbasePath— defaults tohttps://api.searchmcp.io
Schemas & Types
All request/response schemas and types are generated from the OpenAPI spec and exported:
import { SearchRequest, SearchResponse, SearchStatus, } from "@searchmcp/client";
See the interactive API Reference for details:
- SearchRequest model
- SearchResponse model
Development
pnpm install pnpm generate # re-generate from OpenAPI spec pnpm build
License
MIT — see LICENSE
관련 서버
Bright Data
스폰서Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Plasmate MCP
Agent-native headless browser that converts web pages to structured Semantic Object Model (SOM) JSON -- 4x fewer tokens than raw HTML with lower latency on Claude and GPT-4o.
CrawlForge MCP
CrawlForge MCP is a production-ready MCP server with 18 web scraping tools for AI agents. It gives Claude, Cursor, and any MCP-compatible client the ability to fetch URLs, extract structured data with CSS/XPath selectors, run deep multi-step research, bypass anti-bot detection with TLS fingerprint randomization, process documents, monitor page changes, and more. Credit-based pricing with a free tier (1,000 credits/month, no credit card required).
Yanyue MCP
Fetches cigarette data and information from Yanyue.cn.
BrowserAct
BrowserAct MCP Server is a standardized MCP service that lets MCP clients connect to the BrowserAct platform to discover and run browser automation workflows, access results/files and related storage, and trigger real-world actions via natural language.
Chrome Debug
Automate Chrome via its debugging port with session persistence. Requires Chrome to be started with remote debugging enabled.
Skrapr
An intelligent web scraping tool using AI and browser automation to extract structured data from websites.
Firecrawl MCP
Adds powerful web scraping and search capabilities to LLM clients like Cursor and Claude.
ZenRows MCP
ZenRows MCP gives your agent access to the entire web, including every site that blocks bots.
deadlink-checker-mcp
Dead link checker MCP server - find broken links, redirects, and timeouts on any website.
Configurable Puppeteer MCP Server
A configurable MCP server for browser automation using Puppeteer.