- How MCP servers work
- How to set up a local MCP server that´s able to connect with our SEO API
- Prompt your AI agent and receive real-time SEO insights (not AI hallucinations)
How do MCP servers work?
MCP (Model Context Protocol) servers are designed to provide AI agents direct access to data that they normally can’t access. Think of databases, APIs and other private data sets that typically sit behind authentication barriers or firewalls.
In this guide we’ll show you how to install our MCP server, so you can easily connect your AI tools with the SEO Review Tools API.
The benefits
Large Language Models (LLMs) don’t have access to real-time SEO data. While they excel at providing semantically related keywords, they lack access to crucial metrics like search volume, difficulty, or current search trends. The same limitations apply to backlink data and traffic estimates.
Connecting your AI agent to our MCP server allows it to access live, up-to-date data from the APIs, providing it with real-time insights for more accurate and effective SEO analysis and strategy.
How to Prompt to receive SEO insights?
- Provide me with a table of directly related keywords for “topic X” and include: search volume and search volume trends.
- Extract the top 10 URLs from SERP results for “keyword X” and analyze their backlink profiles.
- Show me the backlinks for “URL x” that are forum links.
- Analyse this content and provide me with a list of SEO recommendations.
Included SEO data insights
- Backlinks data →
Get detailed insights for your domain and competitor sites, including total links, referring domains, anchor texts, unique IPs and more.. - Keywords insights →
Access accurate keyword metrics such as search volume, keyword difficulty, CPC, and organic competition. - Website traffic estimates →
Analyze traffic estimates for any domain globally or regionally. - SERP analysis →
Understand ranking patterns, AI overviews, and competing pages for the keywords that you’re targetting. - SEO Content optimization →
Get actionable recommendations for readability, semantic relevance, and topical coverage. - Domain authority scores →
Evaluate the authority and trustworthiness of any domain. - Plagiarism detection →
Detect duplicate or closely similar text across the web and protect your brand’s credibility.
MCP Clients
You can connect SEO Review Tools MCP server to your MCP client of choice. Here are some examples:
- Claude Desktop (example included)
- Visual Studio Code
- Postman Desktop (example included)
- Copilot Studio
- OpenAI Agents SDK
- And more..
The MCP server [local / remote]
The MCP server can either run locally or remote, in the examples below we’re connecting with API trough a local MCP setup using Node JS. But the code can also be deployed to a remote Node JS server.
(Additionally the provided code can be converted from JS to other programming languages like Python or TypeScript)
Requirements
Before starting, please ensure you have:
Installation & Setup
1. Download SEO Review Tools MCP server
2. Install dependencies
Run from your project’s root directory:
npm install
3. Set tool environment variables
In the .env file, you’ll see environment variable placeholder.
Register for a subscription SEO Review Tools API key → and add your private Key.
SEO_API_WORKSPACE_API_KEY=
How to connect the SEO Review Tools MCP server to Claude Desktop?
Follow these steps to connect the SEO Review Tools MCP server to Claude Desktop.
Step 1: Note the full path to node and the mcpServer.js
Step 2. Open Claude Desktop → Settings → Developers → Edit Config and add a new MCP server:
Restart Claude Desktop to activate.
Connect the MCP Server to Postman
Step 1: Download SEO Review Tools MCP server →.
Step 2: Download Postman Desktop.
Step 3: Set the type of the MCP request to STDIO and set the command to node </absolute/path/to/mcpServer.js>.
Step 4: Connect with the SEO Review Tools APIs using Postman.
Get the new Chrome Extension!
Chrome extension
