ActionKit by Paragon + mcp-agent: Complete MCP Integration
ActionKit by Paragon is a MCP server that Connect to 130+ SaaS integrations (e.g. Slack, Salesforce, Gmail) with Paragon’s ActionKit API..
When integrated with mcp-agent, you can:
- Connect to 130+ SaaS applications via ActionKit API
- Handle OAuth and API authentication for integrations
- Execute custom OpenAPI action definitions
This guide provides step-by-step instructions to set up ActionKit by Paragon in mcp-agent, including configuration, examples, and troubleshooting.
What You'll Achieve
After completing this setup:
- ActionKit by Paragon will be fully integrated and operational
- You can use ActionKit by Paragon tools directly in mcp-agent
- All ActionKit by Paragon capabilities will be available for your workflows
- Access to 4 different tools
Prerequisites
Before starting, ensure you have:
- Node.js 22.14.0
- npm
- Paragon account
- Paragon project identifier from dashboard
- RS256 JWT signing key for authentication
- mcp-agent installed and configured
- Compatible operating system (Python 3.9+, pip Installation, uv Installation, Temporal (Optional))
Installation
Step 1: Install ActionKit by Paragon
Install using npm:
git clone https://github.com/useparagon/paragon-mcp.git && cd paragon-mcp && npm install
Verify installation:
npm run start
Configuration
Step 2: Configure mcp-agent
- Open mcp-agent settings
- Navigate to MCP server configuration
- Add ActionKit by Paragon server with appropriate settings
- Save and restart if needed
Examples
Once configured, you can use ActionKit by Paragon in mcp-agent:
Schedule Team Meeting
Create a Google Calendar event and notify team via Slack
Ask mcp-agent: "Schedule a team standup for tomorrow at 9 AM and send a Slack notification to the dev-team channel"
Expected Result: Calendar event created and Slack message sent with meeting details
Create Sales Lead
Add new lead to Salesforce from customer inquiry
Ask mcp-agent: "Create a new lead in Salesforce for John Doe from Acme Corp with email [email protected]"
Expected Result: Lead record created in Salesforce with contact information and follow-up tasks
Email Campaign Follow-up
Send follow-up emails via Gmail for marketing campaign
Ask mcp-agent: "Send a follow-up email to all prospects who opened our product demo email last week"
Expected Result: Targeted emails sent to qualified prospects with personalized content
Multi-Platform Data Sync
Sync customer data between HubSpot and Salesforce
Ask mcp-agent: "Update all HubSpot contacts that were modified today in our Salesforce CRM"
Expected Result: Contact records synchronized with latest information across both platforms
Testing Your Setup
- Launch mcp-agent
- Verify ActionKit by Paragon is available in the tools list
- Test basic ActionKit by Paragon functionality
Troubleshooting
Common Issues
JWT Authentication Failed
Symptoms: 401 Unauthorized errors, Invalid token messages
Cause: Incorrect SIGNING_KEY or expired credentials
Solution:
- Verify SIGNING_KEY matches private key from Paragon dashboard
- Ensure key is in correct RS256 format
- Check PROJECT_ID is correct for your account
- Regenerate keys if necessary
Integration Not Available
Symptoms: Service not found errors, Integration disabled messages
Cause: Integration not enabled in Paragon project or LIMIT_TO_INTEGRATIONS restriction
Solution:
- Enable required integrations in Paragon dashboard
- Remove or update LIMIT_TO_INTEGRATIONS environment variable
- Verify integration is available in your Paragon plan
- Check integration-specific requirements
User Authorization Required
Symptoms: OAuth flow errors, Permission denied messages
Cause: User has not authorized the integration or scope issues
Solution:
- Guide user through OAuth authorization flow
- Check required scopes for the integration
- Verify callback URLs are configured correctly
- Re-authorize if tokens are expired
Server Connection Timeout
Symptoms: Connection timeouts, SSE endpoint not responding
Cause: Server not running or network connectivity issues
Solution:
- Start server with npm run start
- Verify PORT is not in use by another service
- Check firewall settings allow connections
- Test endpoint with curl: curl http://localhost:3001/health
Import Error - Module Not Found
Symptoms: ModuleNotFoundError: No module named mcp_agent, Import fails
Cause: mcp-agent not installed or wrong Python environment
Solution:
- Verify installation: pip show mcp-agent
- Ensure using correct Python environment/virtualenv
- Reinstall: pip install --upgrade mcp-agent
- Check Python version is 3.9 or higher
MCP Server Connection Failures
Symptoms: Server not starting, Connection timeout, Tool execution errors
Cause: Invalid MCP server configuration or missing dependencies
Solution:
- Verify npx is installed and accessible (required for stdio servers)
- Check MCP server package name and arguments are correct
- Test server independently: npx -y @modelcontextprotocol/server-filesystem /path
- Review agent logs for detailed error messages
- Ensure required environment variables are set
LLM API Authentication Errors
Symptoms: 401 Unauthorized, API key invalid, Provider authentication failed
Cause: Missing or incorrect API keys for LLM provider
Solution:
- Set environment variables: ANTHROPIC_API_KEY, OPENAI_API_KEY, etc.
- Verify API key is valid and has correct permissions
- Check API key format matches provider requirements
- Pass api_key parameter explicitly in Agent initialization
Workflow Execution Failures
Symptoms: Workflow hangs, Timeout errors, Incomplete results
Cause: Workflow pattern misconfiguration or task complexity
Solution:
- Increase timeout values for long-running tasks
- Break complex workflows into smaller steps
- Verify all workflow dependencies are available
- Check Temporal backend is running (for production deployments)
- Review workflow logs for specific error messages
Temporal Backend Connection Issues
Symptoms: Cannot connect to Temporal, Workflow registration fails, Worker errors
Cause: Temporal server not running or misconfigured
Solution:
- Verify Temporal server is running: temporal server health
- Check Temporal connection settings (host, port, namespace)
- Ensure Temporal workers are registered correctly
- Review Temporal server logs for connection errors
- Start local Temporal dev server: temporal server start-dev
Performance Issues with Large Workflows
Symptoms: Slow execution, High memory usage, Timeout errors
Cause: Inefficient workflow design or resource constraints
Solution:
- Use map-reduce pattern for parallelizable tasks
- Implement batching for large data processing
- Enable Temporal backend for better resource management
- Monitor agent memory usage and optimize task size
- Consider streaming responses for large outputs
ActionKit by Paragon not appearing in mcp-agent
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check ActionKit by Paragon installation
- Restart mcp-agent
- Check logs for error messages
Next Steps
Now that ActionKit by Paragon is integrated with mcp-agent:
- Explore all ActionKit by Paragon capabilities through mcp-agent
- Check out other MCP servers that work with mcp-agent
- Join the MCP community for tips and support
- Consider contributing to ActionKit by Paragon development
Need Help?
- Search for ActionKit by Paragon documentation
- Check the mcp-agent MCP guide
- Join the MCP community discussions