# XMLRiver MCP Toolkit

> XMLRiver MCP Toolkit is an MCP server for marketing and seo. Google and Yandex results, Wordstat demand and position checks via your XMLRiver account. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Platforms:** CLI, self-hosted
- **Repository:** https://github.com/dietbear13/xmlriver_mcp
- **MCP Registry name:** io.github.dietbear13/xmlriver-mcp-toolkit
- **Categories:** [marketing and SEO](https://ai-powered.com/categories/marketing-and-seo), [web search and scraping](https://ai-powered.com/categories/web-search-and-scraping)
- **Listing updated:** 2026-11-18

## About

This is an independent project and not an official XMLRiver product. It needs your own XMLRiver account, with the user ID and API key passed as environment variables. The README is in Russian.

Beyond single lookups, a batch tool takes up to 100 phrases per call and runs up to nine requests in parallel, saving results to disk as they arrive so a repeated job reuses stored phrases and pages. The README names serp, wordstat_top, wordstat_history and get_balance as tools, and it notes there is no built-in scheduler or background queue.

It is aimed at SEO specialists who want to ask for keyword expansions, demand history, rank checks across regions and engines, or an account balance in plain language.

## Features

- **Wordstat expansions:** Expands a phrase with frequency counts, optionally with similar queries.
- **Demand history:** Returns Wordstat data for a chosen period to show seasonality.
- **Live results:** Collects Google or Yandex links and titles for a region and device.
- **Position checks:** Finds every occurrence and position of a domain among organic results.
- **Batch mode:** Handles up to 100 phrases per call, nine at a time, and saves results.
- **Balance check:** Shows the XMLRiver balance and per-request cost.

## Good for

- Expand a seed keyword with Wordstat frequencies
- Check where a site ranks in Yandex and Google for a phrase list
- Compare results across regions and search engines
- Look at seasonal demand for a query
- Check XMLRiver balance before a large run

## Install

### Claude Code (Terminal)

```sh
claude mcp add xmlriver-mcp-toolkit --env XMLRIVER_USER='<XMLRIVER_USER>' --env XMLRIVER_KEY='<XMLRIVER_KEY>' -- uvx xmlriver-mcp-toolkit
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "xmlriver-mcp-toolkit": {
      "command": "uvx",
      "args": [
        "xmlriver-mcp-toolkit"
      ],
      "env": {
        "XMLRIVER_USER": "<XMLRIVER_USER>",
        "XMLRIVER_KEY": "<XMLRIVER_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "xmlriver-mcp-toolkit": {
      "command": "uvx",
      "args": [
        "xmlriver-mcp-toolkit"
      ],
      "env": {
        "XMLRIVER_USER": "<XMLRIVER_USER>",
        "XMLRIVER_KEY": "<XMLRIVER_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "xmlriver-mcp-toolkit": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "xmlriver-mcp-toolkit"
      ],
      "env": {
        "XMLRIVER_USER": "<XMLRIVER_USER>",
        "XMLRIVER_KEY": "<XMLRIVER_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "xmlriver-mcp-toolkit": {
      "command": "uvx",
      "args": [
        "xmlriver-mcp-toolkit"
      ],
      "env": {
        "XMLRIVER_USER": "<XMLRIVER_USER>",
        "XMLRIVER_KEY": "<XMLRIVER_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "xmlriver-mcp-toolkit": {
      "command": "uvx",
      "args": [
        "xmlriver-mcp-toolkit"
      ],
      "env": {
        "XMLRIVER_USER": "<XMLRIVER_USER>",
        "XMLRIVER_KEY": "<XMLRIVER_KEY>"
      }
    }
  }
}
```

## Tools

- `get_balance`: Check the XMLRiver balance
- `wordstat_top`: Expand a phrase with Wordstat frequencies
- `wordstat_history`: Get demand history for a query over a period
- `serp`: Collect Google or Yandex search results
- `batch`: Process up to 100 phrases in one call and save results

## FAQ

### What do I need to use it?

An XMLRiver account with balance, plus its user ID and API key.

### How is it installed?

Through uvx with the xmlriver-mcp-toolkit package, or a pip install; Python 3.11 or newer is needed for pip.

### Does it read a .env file?

Not by itself; the client or launch script must load it and pass the values.

### Is it official?

No, the README says it is independent.

### Which clients are covered?

Setup examples cover Claude Desktop, Claude Code, Cursor and Codex.

### How do I add XMLRiver MCP Toolkit to Claude Code?

Run this command in your terminal: claude mcp add xmlriver-mcp-toolkit --env XMLRIVER_USER='<XMLRIVER_USER>' --env XMLRIVER_KEY='<XMLRIVER_KEY>' -- uvx xmlriver-mcp-toolkit

### What are the best alternatives to XMLRiver MCP Toolkit?

The closest alternatives to XMLRiver MCP Toolkit are Scrapling MCP Server, Firecrawl MCP Server, Douyin_TikTok_Download_API, Google Ads + Meta Ads + SEO/GEO MCP and SearXNG Search.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Douyin_TikTok_Download_API](https://ai-powered.com/mcp/douyin-tiktok-download-api): Douyin_TikTok_Download_API is an open-source MCP server for web search and scraping.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [machine_internet](https://ai-powered.com/mcp/machine-internet): machine_internet is an open-source MCP server for web search and scraping.
- [Calven](https://ai-powered.com/mcp/calven): Calven is an MCP server for marketing and seo.
- [acrawl](https://ai-powered.com/mcp/acrawl): acrawl is an open-source MCP server for browser automation.

---
Source: https://ai-powered.com/mcp/xmlriver-mcp-toolkit
