dataforseo-ai

This MCP server provides a suite of DataForSEO AI optimization tools exposed as MCP endpoints. It includes 4 live-LLM tools for real-time responses with citations (chatgpt_live, claude_live, gemini_live, perplexity_live) and 6 LLM-mentions tools for brand monitoring and competitive analysis (search_mentions, top_domains, top_pages, aggregated_metrics, cross_aggregated_metrics, plus related metrics). You can query the server to fetch brand mentions, perform cross-LLM comparisons, or track historical metrics over time. To use, start the Python server as described in the installation steps, then issue requests to the configured MCP endpoints corresponding to the tool you want to run. Each tool will handle API authentication with DataForSEO credentials supplied via environment variables and will return structured results with input parameters, outputs, and credit usage as documented in the project notes.

Prerequisites:\n- Python 3.10+\n- DataForSEO account with API credentials\n- Access to Claude Desktop for testing (optional)\n\nStep 1: Clone or create a project directory\nbash\nmkdir dataforseo-mcp-server\ncd dataforseo-mcp-server\n\n\nStep 2: Create and activate a virtual environment\nbash\n# macOS/Linux\npython3 -m venv venv\nsource venv/bin/activate\n\n# Windows\npython -m venv venv\nvenv\Scripts\activate\n\n\nStep 3: Install dependencies\nbash\npip install -r requirements.txt\n\n\nStep 4: Configure credentials\n1) Copy example env to actual env:\nbash\ncp .env.example .env\n\n2) Edit the .env file to add your DataForSEO credentials:\nbash\nDATAFORSEO_LOGIN=your_email@example.com\nDATAFORSEO_PASSWORD=your_api_password_here\n\nAccess credentials at: https://app.dataforseo.com/api-dashboard\n\nStep 5: Test authentication (optional)\nbash\npython test_auth.py\n\nExpected output should indicate credentials are working.\n\nStep 6: Run the server locally for testing\nbash\npython server.py\n

Tips and notes:\n- Keep credentials secure; do not commit the .env file to version control.\n- The server requires a valid DataForSEO account with API credits.\n- If you run into module or dependency issues, ensure your virtual environment is activated and re-install dependencies with pip install -r requirements.txt.\n- For Claude Desktop integration, use absolute paths in your configurations and restart Claude Desktop after changes.\n- Tools log input parameters, outputs, and credits usage for auditing.\n- You can monitor API quota and errors via the DataForSEO dashboard and status pages.\n- If an environment variable is missing, the server may fail to authenticate; verify that the .env file is loaded correctly by the process.\n- This MCP exposes 10 tools across live-LLM and mentions analytics; you can mix and match tools in multi-LLM workflows for comparative insights.