AgentQL + MCPOmni-Connect: Complete MCP Integration
AgentQL is a MCP server that Enable AI agents to get structured data from unstructured web with AgentQL..
When integrated with MCPOmni-Connect, you can:
- Extract structured data from web pages using natural language
- Scrape web data with structured field definitions
- Monitor web pages for content changes
This guide provides step-by-step instructions to set up AgentQL in MCPOmni-Connect, including configuration, examples, and troubleshooting.
What You'll Achieve
After completing this setup:
- AgentQL will be fully integrated and operational
- You can use AgentQL tools directly in MCPOmni-Connect
- All AgentQL capabilities will be available for your workflows
- Access to 3 different tools
Prerequisites
Before starting, ensure you have:
- API key from AgentQL Dev Portal
- MCPOmni-Connect installed and configured
- Compatible operating system (Python 3.9+, Windows, macOS, Linux, Docker)
Installation
Step 1: Install AgentQL
Configuration
Step 2: Configure MCPOmni-Connect
- Open MCPOmni-Connect settings
- Navigate to MCP server configuration
- Add AgentQL server with appropriate settings
- Save and restart if needed
Examples
Once configured, you can use AgentQL in MCPOmni-Connect:
E-commerce Product Monitoring
undefined
Ask MCPOmni-Connect: "Extract product details from Amazon search results"
Expected Result: undefined
News Article Analysis
undefined
Ask MCPOmni-Connect: "Get headlines, summaries, and publish dates from news site"
Expected Result: undefined
Social Media Insights
undefined
Ask MCPOmni-Connect: "Extract post engagement from social media feeds"
Expected Result: undefined
Testing Your Setup
- Launch MCPOmni-Connect
- Verify AgentQL is available in the tools list
- Test basic AgentQL functionality
Troubleshooting
Common Issues
Command Not Found
Symptoms: mcpomni-connect: command not found, CLI not accessible
Cause: Package not installed or not in PATH
Solution:
- Verify installation: pip show mcpomni-connect
- Ensure Python scripts directory is in PATH
- Try running with python -m: python -m mcpomni_connect
- Reinstall: pip install --upgrade mcpomni-connect
Configuration File Not Found
Symptoms: FileNotFoundError: mcp_config.yaml, Config not loading
Cause: Config file missing or incorrect path
Solution:
- Verify config file exists at specified path
- Use absolute path: --config /full/path/to/mcp_config.yaml
- Check file name is exactly mcp_config.yaml (case-sensitive)
- Validate YAML syntax with yamllint or online validator
MCP Server Connection Failures
Symptoms: Server not responding, Connection timeout, Transport error
Cause: Invalid server configuration or transport issues
Solution:
- Verify transport type matches server capabilities (stdio, sse, http, docker, npx)
- For stdio: ensure command and args are correct
- For SSE/HTTP: verify URL is accessible and server is running
- For Docker: ensure Docker daemon is running and image exists
- Check environment variables are set (e.g., GITHUB_TOKEN)
- Test server manually outside MCPOmni-Connect
Agent Mode Not Working
Symptoms: Agent fails to execute task, Reasoning loop errors, Tool calls failing
Cause: Insufficient LLM configuration or tool access issues
Solution:
- Ensure LLM API key is configured (OpenAI, Anthropic, etc.)
- Verify agent has access to necessary MCP server tools
- Check task description is clear and actionable
- Review agent logs for detailed error messages
- Try simpler task first to verify agent functionality
Orchestrator Mode Failures
Symptoms: Plan execution fails, Step coordination errors, Agent communication issues
Cause: Invalid plan structure or agent dependencies
Solution:
- Verify plan steps are clearly defined and sequential
- Ensure each step can be completed with available tools
- Check inter-agent communication is working
- Review orchestrator logs for step-by-step execution details
- Test individual plan steps in agent mode first
Docker Transport Errors
Symptoms: Container not starting, Docker connection refused, Port binding errors
Cause: Docker configuration or runtime issues
Solution:
- Verify Docker is installed and running: docker ps
- Check Docker image exists: docker images
- Ensure ports are not already in use
- Review container logs: docker logs <container_name>
- Verify network configuration allows container communication
FastAPI Integration Issues
Symptoms: Import errors, Async execution failures, Endpoint not responding
Cause: Incorrect async configuration or FastAPI version mismatch
Solution:
- Use run_agent_async() for async FastAPI endpoints
- Ensure FastAPI version is compatible (0.100.0+)
- Verify MCPOmniClient is initialized outside request handlers
- Check async event loop configuration
- Review FastAPI logs for detailed error messages
AgentQL not appearing in MCPOmni-Connect
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check AgentQL installation
- Restart MCPOmni-Connect
- Check logs for error messages
Next Steps
Now that AgentQL is integrated with MCPOmni-Connect:
- Explore all AgentQL capabilities through MCPOmni-Connect
- Check out other MCP servers that work with MCPOmni-Connect
- Join the MCP community for tips and support
- Consider contributing to AgentQL development
Need Help?
- Search for AgentQL documentation
- Check the MCPOmni-Connect MCP guide
- Join the MCP community discussions