Serpstat MCP Server
A TypeScript server that integrates Serpstat SEO API with Anthropic's Model Context Protocol (MCP), enabling AI assistants like Claude to access comprehensive SEO data and analysis tools.
Potencialize seu agente
Instalação do publicador. Não é um endpoint do PlugMCP.
Host a copy with our keys and logs.
Ainda não há uma versão empacotada no registro. Siga o README do repositório.
URL remota ou um comando na sua máquina? Como as duas instalações diferem
Rodar no PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
AbrirDo publicador
A TypeScript server that integrates Serpstat SEO API with Anthropic's Model Context Protocol (MCP), enabling AI assistants like Claude to access comprehensive SEO data and analysis tools.
MCP (Model Context Protocol) server for integration with Serpstat API, implementing api methods for a SEO analysis. JS/TS version
The Model Context Protocol (MCP) is an open standard developed by Anthropic that enables AI assistants to securely connect to external data sources and tools. This server implements MCP to provide Claude and other compatible AI assistants with access to Serpstat's powerful SEO analytics API.
This project implements a TypeScript server that provides an API interface for working with Serpstat tools via the MCP protocol. The server supports request handling, parameter validation, logging, and working with multiple SEO analysis tools.
npm install -g @serpstat/serpstat-mcp-server
npm install @serpstat/serpstat-mcp-server
Set the following environment variables (can be in .env file):
SERPSTAT_API_TOKEN — Your Serpstat API token (required)SERPSTAT_API_URL — Serpstat API URL (default: https://api.serpstat.com/v4)LOG_LEVEL — Logging level: error, warn, info, debug (default: info)SERPSTAT_ENABLED_CATEGORIES — Filter tools by categories (optional, comma-separated, default: all categories enabled)Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add to your Gemini CLI config:
Linux: ~/.gemini/settings.json
{
"mcpServers": {
"serpstat": {
"command": "npx",
"args": ["-y", "@serpstat/serpstat-mcp-server"],
"env": {
"SERPSTAT_API_TOKEN": "YOUR_SERPSTAT_API_TOKEN_HERE",
"LANG": "en_US.UTF-8",
"LC_ALL": "en_US.UTF-8"
}
}
}
}
For local development, use the full path:
{
"mcpServers": {
"serpstat": {
"command": "node",
"args": ["/path/to/node_modules/serpstat-mcp-server/dist/index.js"],
"env": {
"SERPSTAT_API_TOKEN": "YOUR_SERPSTAT_API_TOKEN_HERE"
}
}
}
}
You can limit which tools are available by specifying SERPSTAT_ENABLED_CATEGORIES environment variable. This is useful for:
Available categories:
domain - Domain analysis tools (domain info, competitors, domain keywords, etc.)keywords - Keyword research tools (keyword suggestions, search volume, difficulty, etc.)backlinks - Backlink analysis tools (backlink summary, anchors, referring domains, etc.)url - URL analysis tools (URL traffic, competitors, keywords, etc.)projects - Project management tools (create, list, delete projects)credits - Credits and usage monitoring toolsrt - Rank tracking tools (rank history, SERP tracking, etc.)audit - Site audit tools (full site SEO audit, error reports, etc.)page-audit - One-page audit tools (single page analysis, on-page SEO, etc.)Example: Enable only keyword and domain tools
{
"mcpServers": {
"serpstat": {
"command": "npx",
"args": ["-y", "@serpstat/serpstat-mcp-server"],
"env": {
"SERPSTAT_API_TOKEN": "YOUR_SERPSTAT_API_TOKEN_HERE",
"SERPSTAT_ENABLED_CATEGORIES": "keywords,domain"
}
}
}
}
Example: Enable only backlink analysis
{
"mcpServers": {
"serpstat": {
"command": "npx",
"args": ["-y", "@serpstat/serpstat-mcp-server"],
"env": {
"SERPSTAT_API_TOKEN": "YOUR_SERPSTAT_API_TOKEN_HERE",
"SERPSTAT_ENABLED_CATEGORIES": "backlinks"
}
}
}
}
Default behavior (all tools enabled):
If SERPSTAT_ENABLED_CATEGORIES is not specified or is empty, all tools are available (65 total tools across all categories).
After installation and configuration in Claude Desktop, you can ask Claude:
iphone, samsung, googel pixel ] including search volume, CPC, and difficulty"pizza delivery keyword with visibility metrics"laptop computers keyword showing positions, domains and SERP features"Common search engine codes:
g_us - Google USAg_uk - Google United Kingdomg_ca - Google Canadag_au - Google Australiag_de - Germanyg_fr - Google Franceg_es - Google Spaing_it - Google Italyg_pl - Google Polandg_ua - Google UkraineSee a full list of Search Engines Short Names
"Command not found: serpstat-mcp-server"
-g flagnpm config get prefixnpm uninstall -g @serpstat/serpstat-mcp-server && npm install -g @serpstat/serpstat-mcp-server"API token error" or "Unauthorized"
SERPSTAT_API_TOKEN is set correctly in your environment"Module not found" errors
npm installnpm run clean && npm run buildClaude Desktop doesn't recognize the server
serpstat-mcp-server in terminal"Can't find npx"
Rate limit errors
Enable debug logging by setting:
export LOG_LEVEL=debug
Or in your Claude Desktop config:
{
"mcpServers": {
"serpstat": {
"command": "npx",
"args": ["-y", "@serpstat/serpstat-mcp-server"],
"env": {
"SERPSTAT_API_TOKEN": "YOUR_TOKEN_HERE",
"LANG": "en_US.UTF-8",
"LC_ALL": "en_US.UTF-8",
"LOG_LEVEL": "debug"
}
}
}
}
Clone the repository:
git clone [email protected]:SerpstatGlobal/serpstat-mcp-server-js.git
cd serpstat-mcp-server-js
Install dependencies:
npm install
Set environment variables:
cp .env.example .env
# Edit .env with your Serpstat API token
Build the project:
npm run build
Start the server:
npm start
For development mode (auto-reload):
npm run dev
To run tests:
npm test
Run specific test file:
npx jest src/__tests__/services/keyword_tools.test.ts
Run specific test by name:
npx jest --testNamePattern="methodName"
npm run build — Compile TypeScript sources to JavaScript (output in dist/)npm start — Run the compiled server from dist/npm run dev — Run the server in development mode with hot-reloadnpm test — Run all testsnpm run lint — Run lintingnpm run clean — Clean build directoryserpstat-mcp-server/
├── src/
│ ├── index.ts # Entry point
│ ├── server.ts # Main MCP server
│ ├── handlers/ # Tool handlers
│ ├── services/ # Services for Serpstat API
│ ├── types/ # Data types
│ ├── utils/ # Utilities (config, logger, validation)
│ └── __tests__/ # Tests
├── dist/ # Compiled JavaScript (after build)
├── package.json
├── tsconfig.json
├── README.md
└── .env.example
By default, most Serpstat plans have 1 RPS (1 request per second) - this is sufficient for most tasks. If you need higher throughput, contact Serpstat support to discuss plan upgrades.
Important: The server respects rate limits automatically. If you encounter rate limit errors, wait before making additional requests.
We welcome contributions! Please follow these steps:
git checkout -b feature/amazing-featurenpm testgit commit -m 'Add amazing feature'git push origin feature/amazing-featurenpm run lintSee CHANGELOG.md for details about changes in each version.
The most effective way to receive support from Serpstat is to use their live chat feature directly within the platform. Alternatively, you can email them at [email protected].
MIT License
This project is under MIT license, which means you can copy, use, modify, and even sell any part of this code without any hassle.
With love, Serpstat R&D Team
MCP (Model Context Protocol) server for integration with Serpstat API, implementing api methods for a SEO analysis. JS/TS version
Ferramentas
Ainda não há lista de ferramentas. Servidores remotos recebem uma após a primeira verificação de saúde.
Perguntas frequentes
Copie nesta página a configuração stdio para Cursor, Claude Desktop, Claude Code ou VS Code. Ela usa a instalação do publicador, não um proxy do PlugMCP.
Este registro não lista nenhuma variável de ambiente obrigatória.
Serpstat MCP Server Js roda localmente via stdio.
Última verificação: 2026-10-27. MCP (Model Context Protocol) server for integration with Serpstat API, implementing api methods for a SEO analysis. JS/TS version