The Model Context Protocol (MCP) enables standardized communication between AI applications and data sources. Build custom MCP clients to integrate ContextGate into any application or workflow.
This guide shows you how to implement a custom MCP client that connects to ContextGate, enabling integration with any MCP-compatible AI system or custom application.
📋 Prerequisites
- Node.js 18+ or Python 3.10+
- Understanding of JSON-RPC protocol
- ContextGate account with API bearer token
- Familiarity with async programming (optional but recommended)
Understanding MCP
MCP defines a standard protocol for AI applications to access external data and tools. An MCP server exposes:
- Resources: Data sources that can be read
- Tools: Functions that can be called
- Prompts: Templates for common interactions
Get Your ContextGate Bearer Token
Navigate to the Install page in your ContextGate workspace. Click "View API Token" and copy your bearer token for authentication.
💡 Your token can be found on the Install page .
Keep your bearer token secure! Never commit it to version control.
Configure Your Toolbox (Optional)
On the Install page, you can customize which tools, connections, and datasets are available through ContextGate. This allows you to:
- Limit access to specific connections (e.g., only Salesforce, not QuickBooks)
- Enable only certain tools or operations
- Control which datasets are accessible
Toolbox Manager Interface:
TypeScript/Node.js MCP Client
Install the MCP SDK and create a basic client:
Create a ContextGate MCP client:
Python MCP Client
Install the MCP Python SDK:
Create a Python MCP client:
Direct REST API Integration
For simpler use cases, use ContextGate's REST API directly:
cURL Example:
JavaScript/Fetch:
Python/Requests:
Advanced: Error Handling & Retry Logic
Implement robust error handling and retry mechanisms:
📚 ContextGate API Endpoints
| Endpoint | Method | Description |
|---|---|---|
| /v1/query | POST | Query data from connected apps |
| /v1/connections | GET | List available connections |
| /v1/resources | GET | List datasets for a connection |
| /v1/health | GET | Check API health status |
Authentication
All API requests require a bearer token in the Authorization header: Authorization: Bearer YOUR_TOKEN
🔧 Troubleshooting
401 Unauthorized
- Verify bearer token is correct and not expired
- Check Authorization header format: "Bearer TOKEN"
- Ensure token has necessary permissions in ContextGate
Connection Timeouts
- Increase timeout values in your HTTP client
- Check network connectivity and firewall settings
- Verify ContextGate API is accessible from your environment
Rate Limiting
- Implement exponential backoff for retries
- Check response headers for rate limit information
- Consider caching responses for frequently accessed data
🚀 Next Steps
- Build Custom Tools: Create domain-specific integrations for your workflow
- Add Caching: Implement response caching for better performance
- Monitor Usage: Track API usage and implement alerting for errors