seo-research
A free SEO research tool using Model Context Protocol (MCP) powered by Ahrefs data. Get backlink analysis, keyword research, traffic estimation, and more — directly in your AI-powered IDE.
claude mcp add --transport stdio egebese-seo-research-mcp uvx --python 3.10 seo-mcp \ --env CAPSOLVER_API_KEY="YOUR_API_KEY_HERE"
How to use
The SEO Research MCP integrates powerful SEO analysis tools directly into your IDE or editor via the MCP protocol. It exposes capabilities like backlink analysis, keyword generation, traffic estimation, and keyword difficulty assessments, all accessible through the seo-research tool name. When connected, you can query get_backlinks_list(domain) to pull backlink data, generate keyword ideas with keyword_generator(keyword, country?, search_engine?), estimate site traffic with get_traffic(domain_or_url, country?, mode?), and assess keyword competitiveness using keyword_difficulty(keyword, country?). These tools are designed to work within your coding workflow, allowing you to perform SEO research without leaving your editor. Use the predefined prompts or tool invocations (e.g., #tool_name) to trigger specific analyses and view structured results returned by the MCP server.
How to install
Prerequisites:
- Python 3.10 or higher
- Access to CapSolver API key (for CAPTCHA solving)
- Internet access to install packages
Installation steps:
-
Install the MCP server package from PyPI: pip install seo-mcp
-
Install via uv (optional local environment): uv pip install seo-mcp
-
Verify installation and run the MCP server:
Start the MCP server (example command; your environment may vary)
uvx --python 3.10 seo-mcp
-
Set up the API key in your environment: export CAPSOLVER_API_KEY="YOUR_API_KEY_HERE"
-
If you prefer installing from source: git clone https://github.com/egebese/seo-research-mcp.git cd seo-research-mcp pip install -e .
-
Confirm the server is reachable via MCP client tooling in your IDE or editor integration.
Additional notes
Tips and common considerations:
- Ensure CAPSOLVER_API_KEY is kept secure and is not committed to code repositories.
- The MCP config uses the uvx command with Python 3.10 context; ensure your environment provides this interpreter version.
- If you encounter CAPTCHA-related issues, verify your CapSolver quota and API key validity.
- The examples show integration across several editors (Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Zed). Adapt the mcp_config structure to the editor you are using if it requires a different path or environment variable layout.
- When testing, start with a simple domain query to validate connectivity before performing large-scale data pulls.
Related MCP Servers
cursor-notebook
Model Context Protocol (MCP) server designed to allow AI agents within Cursor to interact with Jupyter Notebook (.ipynb) files
mcp -typescript
DataForSEO API modelcontextprotocol server
PixVerse
Official PixVerse Model Context Protocol (MCP) server that enables interaction with powerful AI video generation APIs.
MCPStack
Stack & Orchestrate MCP Tools — The Scikit-Learn-Pipeline Way , For LLMs
google-search-console
It connects directly to your Google Search Console account via the official API, letting you access key data right from AI tools like Claude Desktop or OpenAI Agents SDK and others .
MCP-Mathematics
A comprehensive Model Context Protocol (MCP) server that turns any AI assistant into a powerful mathematical computation engine.