FetchSERP is a comprehensive SEO and web intelligence toolkit that integrates with AI models via the Model Context Protocol (MCP). It allows AI agents to access real-time search engine results (SERP), perform keyword research, analyze backlinks, and scrape web pages.
What it does: FetchSERP provides a powerful API for competitive research, keyword intelligence, and content strategy. It offers various endpoints for:
- SERP Analysis: Fetch search results from Google, Bing, Yahoo, DuckDuckGo, including AI overviews.
- Keyword Intelligence: Get search volume, suggestions, and competition data.
- Backlinks Analysis: Detailed backlink data for any domain.
- Web Scraping: Scrape web pages with or without JavaScript execution, including proxy support.
- Domain Info: Comprehensive DNS, WHOIS, server, and technology stack details.
- Content Generation: AI-powered content creation for WordPress and social media.
- SEO Analysis: On-page SEO audits.
How to use: FetchSERP can be integrated with AI models like Claude and OpenAI via MCP in two primary ways:
-
Node.js MCP Server (stdio): Run a local MCP server using
npxfrom thefetchSERP/fetchserp-mcp-server-nodeGitHub repository. This requires setting yourFETCHSERP_API_TOKENas an environment variable. Example configuration for Claude Desktop:{ "mcpServers": { "fetchserp": { "command": "npx", "args": [ "github:fetchSERP/fetchserp-mcp-server-node" ], "env": { "FETCHSERP_API_TOKEN": "your_fetchserp_api_token_here" } } } } -
Remote MCP Server (SSE): Connect directly to the hosted FetchSERP MCP endpoint via a URL. This is suitable for cloud-based AI applications. Example configuration for Claude API or OpenAI API:
MCP_SERVER_URL=https://www.fetchserp.com/mcp FETCHSERP_API_TOKEN=your_fetchserp_api_token_hereYou would then configure your AI application to use this URL as an MCP server.
Key Features:
- Universal SERP Coverage (Google, Bing, Yahoo, DuckDuckGo)
- Real-time data access
- Natural language interaction with AI agents
- Comprehensive SEO metrics and insights
- Open-source SDKs for Ruby, Node.js, Python
- Credit-based pricing with free credits to start.
Recommend MCP Servers 💡
arxiv-latex-mcp
MCP server that uses arxiv-to-prompt to fetch and process arXiv LaTeX sources for precise interpretation of mathematical expressions in scientific papers.
@wonderwhy-er/desktop-commander
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities
buildkite-mcp-server
Model Context Protocol (MCP) server exposing Buildkite data (pipelines, builds, jobs, tests) to AI tooling and editors.
@hubspot/mcp-server
The HubSpot MCP server securely connects MCP-compatible agent clients to your HubSpot data, enabling AI agents to interact with CRM information, fetch real-time data, and trigger predefined actions.
dida-mcp-server
An MCP server for interacting with TickTick/Dida365 task management service, providing tools to manage tasks, projects, and tags.
vision-tools-mcp
VisionAgent MCP is a lightweight, side-car MCP server that runs locally on STDIN/STDOUT, translating tool calls from an MCP-compatible client into authenticated HTTPS requests to Landing AI’s VisionAgent REST APIs for computer vision and document analysis.