DataForSEO MCP server

The SEO Tools MCP Server provides a seamless way for Large Language Models (LLMs) to interact with DataForSEO and other SEO tools through the Model Context Protocol. This server acts as a bridge, allowing natural language interactions to trigger SEO analysis, keyword research, backlink checks, and more.

Installation

To get started with the SEO Tools MCP Server:

# Clone the repository
git clone https://github.com/Skobyn/dataforseo-mcp-server.git

# Change to the project directory
cd dataforseo-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Before running the server, you need to set up your API credentials:

DataForSEO Setup

DataForSEO is the primary API service used by this server. You'll need to set these environment variables:

# Set environment variables for DataForSEO authentication
export DATAFORSEO_LOGIN="your_login"
export DATAFORSEO_PASSWORD="your_password"

Local Falcon Setup (Optional)

If you want to use Local Falcon tools for local SEO:

# Set Local Falcon API key
export LOCALFALCON_API_KEY="your_localfalcon_api_key"

# Optional: Set custom Local Falcon API URL if needed
# export LOCALFALCON_API_URL="https://custom-localfalcon-url.com/api"

Running the Server

Basic Usage with DataForSEO

# After setting environment variables
npm start

With Both DataForSEO and Local Falcon

# After setting all environment variables
npm start

Available Tools

The server exposes numerous SEO tools across different categories:

SERP API Tools

Search engine results data from various search engines:

• serp_google_organic_live - Get real-time Google organic search results
• serp_google_maps_live - Get Google Maps search results

Keywords Data Tools

For keyword research and analysis:

• keywords_google_ads_search_volume - Get search volume for keywords
• keywords_google_ads_keywords_for_site - Get keyword suggestions for a domain
• keywords_google_trends_explore - Explore keyword trends over time

DataForSEO Labs Tools

Advanced SEO analytics:

• labs_google_keyword_ideas - Get keyword ideas based on seed keywords
• labs_google_related_keywords - Find related keywords
• labs_google_domain_rank_overview - Get domain ranking overview

Backlinks Tools

For backlink analysis:

• backlinks_summary - Get a summary of a domain's backlink profile
• backlinks_backlinks - Get a list of backlinks for a domain
• backlinks_referring_domains - Get referring domains for a target

Local Falcon Tools (If Configured)

For local SEO analysis:

• localfalcon_calculate_grid_points - Calculate grid points around a base coordinate
• localfalcon_search_gmb_locations - Search for Google My Business locations
• localfalcon_run_grid_search - Run a full grid search for local rankings

Integration with LLMs

This server implements the Model Context Protocol, making it compatible with LLMs like Claude. To use it with your preferred LLM, you'll need to integrate it according to the platform's specific MCP implementation.

The server uses stdio as its transport layer, which simplifies integration with various LLM platforms.

Example Usage

Here's a simple example of how an LLM might interact with the server:

1. LLM receives a user query like "What's the search volume for 'SEO tools'?"
2. LLM identifies this requires the keywords_google_ads_search_volume tool
3. LLM makes an MCP call with the appropriate parameters
4. The server processes the request and returns the data
5. LLM formats and presents the information to the user

For more detailed examples, check the examples directory in the repository.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "dataforseo" '{"command":"npm","args":["start"],"env":{"DATAFORSEO_LOGIN":"","DATAFORSEO_PASSWORD":""}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "dataforseo": {
            "command": "npm",
            "args": [
                "start"
            ],
            "env": {
                "DATAFORSEO_LOGIN": "",
                "DATAFORSEO_PASSWORD": ""
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "dataforseo": {
            "command": "npm",
            "args": [
                "start"
            ],
            "env": {
                "DATAFORSEO_LOGIN": "",
                "DATAFORSEO_PASSWORD": ""
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect