MCP Server

This guide explains how to install the SE Ranking MCP Server and connect it to a supported AI assistant.

• What is MCP?
• Prerequisites
• API Tokens
• Build the Docker Image
• Connect to Claude Code
• Connect to Claude Desktop
• Connect to Gemini CLI
• Example Prompts
• Troubleshooting

What is MCP?

The Model Context Protocol (MCP) is an open standard that connects AI assistants to external tools and data sources. The SE Ranking MCP Server gives AI assistants direct access to SE Ranking’s SEO data and project management APIs, enabling natural-language queries for:

• Keyword research and competitive analysis
• Backlink analysis and monitoring
• Domain traffic and ranking insights
• Website audits and technical SEO
• AI search visibility tracking
• Project and rank tracking management

Prerequisites

Before you begin, you’ll need:

• SE Ranking account with the API access. If you don’t have one, sign up here.
• Docker. Download Docker.
• An MCP-compatible AI client:

API tokens

The MCP server supports two types of API access. You can use one or both depending on which tools you need.

You can find instructions on how to generate your API tokens here.

Get your tokens from the API Dashboard.

Using only one token? Omit the -e lines for the token you don’t have in the setup commands below. You’ll only see tools for the API you’ve configured.

Build the Docker image

All three clients use the same Docker image. Build it once:

git clone https://github.com/seranking/seo-data-api-mcp-server.git

cd seo-data-api-mcp-server

docker compose build

Verify the build:

docker image ls | grep se-ranking

You should see se-ranking/seo-data-api-mcp-server in the output. Once built, proceed to the setup for your chosen client.

To update later:

cd seo-data-api-mcp-server

git pull origin main

docker compose build

Connect to Claude Code

Claude Code is Anthropic’s agentic CLI tool. It runs in your terminal and can execute multi-step workflows, save results to files, and chain 15+ API calls in a single task.

Additional requirements:

• Requires a Claude subscription or Anthropic Console account

Step 1 — Install Claude Code

macOS, Linux, WSL:

curl -fsSL https://claude.ai/install.sh | bash

Windows PowerShell:

irm https://claude.ai/install.ps1 | iex

Windows CMD:

curl -fsSL https://claude.ai/install.cmd -o install.cmd && install.cmd && del install.cmd

After the installation process completes, navigate to your project and start Claude Code:

cd your-awesome-project

claude

If you encounter any issues during installation, consult the troubleshooting guide.

Step 2 — Add the SE Ranking MCP Server

Run the following command. Replace the token values with your actual API tokens.

claude mcp add-json seo-data-api-mcp '{

  "command": "docker",

  "args": ["run", "-i", "--rm", "-e", "DATA_API_TOKEN", "-e", "PROJECT_API_TOKEN", "se-ranking/seo-data-api-mcp-server"],

  "env": {

    "DATA_API_TOKEN": "your-data-api-token",

    "PROJECT_API_TOKEN": "your-project-api-token"

  }

}'

This registers a server named seo-data-api-mcp in your local Claude Code config. The env block passes your tokens to Docker at runtime.

{

  "mcpServers": {

    "seo-data-api-mcp": {

      "command": "docker",

      "args": [

        "run", "-i", "--rm",

        "-e", "DATA_API_TOKEN",

        "-e", "PROJECT_API_TOKEN",

        "se-ranking/seo-data-api-mcp-server"

      ],

      "env": {

        "DATA_API_TOKEN": "your-data-api-token",

        "PROJECT_API_TOKEN": "your-project-api-token"

      }

    }

  }

}

Step 3 — Verify the connection

Start Claude Code and run the /mcp command:

claude

> /mcp

You should see seranking listed with a connected status and 100+ tools available. If the server shows as disconnected, see Troubleshooting.

Connect to Claude Desktop

Claude Desktop is Anthropic’s chat application. It supports MCP through a local configuration file.

Step 1 — Open the configuration file

1. Click the Claude menu and select Settings.
2. Navigate to the Developer tab.
3. Click Edit Config.

The file is located at:

Step 2 — Add the SE Ranking MCP Server

Paste the following into claude_desktop_config.json. Replace the token values with your actual API tokens.

{

  "mcpServers": {

    "seo-data-api-mcp": {

      "command": "docker",

      "args": [

        "run",

        "-i",

        "--rm",

        "-e",

        "DATA_API_TOKEN",

        "-e",

        "PROJECT_API_TOKEN",

        "se-ranking/seo-data-api-mcp-server"

      ],

      "env": {

        "DATA_API_TOKEN": "your-data-api-token",

        "PROJECT_API_TOKEN": "your-project-api-token"

      }

    }

  }

}

Step 3 — Verify the connection

1. Save the file and restart Claude Desktop.
2. Ask Claude: Do you have access to MCP?
3. Claude should respond listing seo-data-api-mcp as an available server.

Connect to Gemini CLI

Gemini CLI is Google’s command-line AI assistant. It supports MCP through its settings file.

Step 1 — Open the settings file

~/.gemini/settings.json

Step 2 — Add the SE Ranking MCP Server

Add the following configuration. Replace the token values with your actual API tokens.

{

  "mcpServers": {

    "seo-data-api-mcp": {

      "command": "docker",

      "args": [

        "run",

        "-i",

        "--rm",

        "-e",

        "DATA_API_TOKEN",

        "-e",

        "PROJECT_API_TOKEN",

        "se-ranking/seo-data-api-mcp-server"

      ],

      "env": {

        "DATA_API_TOKEN": "your-data-api-token",

        "PROJECT_API_TOKEN": "your-project-api-token"

      }

    }

  }

}

Step 3 — Verify the connection

1. You should see SE Ranking tools listed.
2. Save the file and launch Gemini CLI.
3. Ask: List available MCP tools

Example Prompts

These prompts work in any MCP-compatible client. Copy, paste, run.

Quick lookup — single API call:

What's the organic traffic for apple.com in the US market?

Competitive analysis — 5–10 API calls:

Find keyword gaps between apple.com and samsung.com for the US market.

Focus on keywords with difficulty under 30 and volume over 1,000/mo.

Save results to a CSV file.

Full deliverable — 15+ API calls, best with Claude Code:

I'm an SEO consultant analyzing the project management SaaS space.

Using SE Ranking:

1. Get backlink profiles for monday.com, asana.com, and clickup.com

2. Find domains that link to at least 2 of them

3. Pull keyword rankings — find gaps where one ranks top 3 but others don't

4. For the top 5 gaps, pull SERP results to see what content is winning

5. Synthesize into a competitive intelligence brief

Save everything to organized files.

Build with the API — for developers:

Using SE Ranking API from MCP, create a Python script that pulls

keyword rankings for my top 100 keywords every Monday and sends

a Slack summary if any keyword drops more than 5 positions.

The MCP server contains SE Ranking’s full API documentation — every endpoint, parameter, and example response. Claude Code reads the schema directly and writes production-ready code without you needing to visit the docs site.

For more prompts, see Prebuilt SEO Prompts for SE Ranking MCP Server.

Troubleshooting

Below are some issues you may encounter when getting the MCP server to connect:

• Invalid JSON in Claude/Gemini config
• Incorrect Docker image name
• Missing API tokens

If you need further assistance, contact us at [email protected].

How to troubleshoot:

Docker: “Connection closed” or server not starting

• Verify Docker is running: docker ps
• Verify the image exists: docker image ls | grep se-ranking
• Rebuild if needed: docker build -t se-ranking/seo-data-api-mcp-server .

No tools appearing

• Check that your API tokens are valid at the API Dashboard.
• If you configured only one token, you’ll see only tools for that API (Data or Project). This is expected.

Claude Code: server not connecting

• Run claude mcp list to check configured servers.
• Run claude mcp get seo-data-api-mcp to inspect the configuration.
• Run /mcp inside Claude Code to check live status.

Claude Desktop: server not appearing after restart

• Validate your JSON at jsonlint.com: a missing comma or bracket breaks the file.
• Ensure Docker Desktop is running before launching Claude Desktop.

Resources

• GitHub: seranking/seo-data-api-mcp-server
• API Dashboard — Get your tokens
• Prebuilt SEO Prompts
• Model Context Protocol spec

Video: SE Ranking MCP in Action

See how the MCP server enables competitor analysis and fast keyword research using AI assistants.