What do I need to use Semrush MCP Server?
You need a Semrush API key (`SEMRUSH_API_KEY`) and Node.js installed. The server and CLI are installed via npm.
@mrkooblu
基本信息
A Model Context Protocol (MCP) server implementation that provides tools for accessing Semrush API data.
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
It is a community-maintained, self-hosted tool that provides Semrush API data through an MCP server for AI assistants (Claude Desktop, Cursor) and a semrush CLI for direct terminal use. It enables keyword research, domain analytics, backlinks, traffic analysis, and competitive intelligence.
Install globally via npm install -g github:mrkooblu/semrush-mcp, then set the SEMRUSH_API_KEY environment variable. Use the semrush CLI for terminal/agent commands or configure the semrush-mcp command in your MCP client’s config (e.g., Claude Desktop or Cursor) using stdio transport.
You need a Semrush API key (`SEMRUSH_API_KEY`) and Node.js installed. The server and CLI are installed via npm.
Yes, a Semrush account with API access is required. Traffic and Audience tools additionally need the .Trends API subscription.
Any MCP-compatible client using stdio transport is supported. Explicit setup examples are provided for Claude Desktop and Cursor.
You can configure `API_RATE_LIMIT_PER_SECOND` (default 10) and `API_CACHE_TTL_SECONDS` (default 300). API requests consume units from your Semrush account.
Use the `semrush units` CLI command or the `semrush_api_units_balance` MCP tool.

Model Context Protocol Servers
Painless E2E Automation for Mobile and Web
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Hindsight: Agent Memory That Learns
评论