MCP

Connect custom tools and APIs to CloudThinker via Model Context Protocol (MCP) for extensible agent capabilities

Model Context Protocol (MCP) enables CloudThinker to connect to custom tools and services. Use MCP to extend agent capabilities with your own connections.

---

What is MCP?

MCP (Model Context Protocol) is an open protocol for connecting AI agents to external tools and data sources. It provides a standardized way to:

• Expose tools that agents can call
• Provide context and data to agents
• Enable custom integrations with any service

---

Setup

1. Prepare MCP Server

   Ensure your MCP server is running and accessible:

   • Supports Server-Sent Events (SSE) transport
   • Has a publicly accessible endpoint (or VPN access)
   • Returns proper MCP protocol responses
2. Create Connection

   Navigate to Connections → MCP and click Add MCP Connection

3. Configure Basic Info

   Enter connection details:

   • Name: Descriptive name for the connection
   • Prefix: Tool prefix (e.g., mytools → mytools_function_name)
4. Configure Transport

   Set up the connection transport:

   • Transport Type: Server-Sent Events
   • URL: Your MCP server endpoint
   • Timeout: Connection timeout (default: 5 seconds)
   • SSE Read Timeout: Event stream timeout (default: 30 seconds)
5. Add Environment Variables

   Configure any required environment variables:

   • API keys
   • Authentication tokens
   • Custom configuration
6. Test & Create

   Test the connection and save

---

Configuration Options

Field	Description	Required
Name	Connection display name	Yes
Prefix	Tool name prefix	Yes
URL	MCP server endpoint	Yes
Timeout	Connection timeout (seconds)	No (default: 5)
SSE Read Timeout	Event stream timeout (seconds)	No (default: 30)
Environment Variables	Key-value pairs for configuration	No

---

Example MCP Server

A simple MCP server that provides a weather lookup tool:

from mcp import Server, Tool

server = Server("weather-tools")

@server.tool()
async def get_weather(location: str) -> str:
    """Get current weather for a location."""
    # Your implementation here
    return f"Weather for {location}: Sunny, 72°F"

if __name__ == "__main__":
    server.run()

Once connected with prefix weather, agents can call:

weather_get_weather(location="San Francisco")

---

Use Cases

Custom Data Sources

Connect proprietary databases or APIs:

• Internal metrics systems
• Custom monitoring tools
• Business intelligence platforms

Specialized Tools

Add domain-specific capabilities:

• Custom compliance checks
• Internal automation scripts
• Legacy system integrations

External Services

Integrate third-party services:

• Communication platforms
• Ticketing systems
• Cloud services not built-in

---

Best Practices

Security

• Use HTTPS endpoints
• Rotate API keys regularly
• Implement proper authentication
• Limit tool permissions

Reliability

• Set appropriate timeouts
• Implement retry logic
• Monitor server health
• Handle errors gracefully

---

Troubleshooting

Connection timeout

• Verify MCP server is running
• Check network connectivity
• Increase timeout values
• Confirm firewall allows traffic

Tool not appearing

• Verify prefix is set correctly
• Check MCP server returns tool definitions
• Ensure protocol version is compatible
• Review server logs for errors

Authentication errors

• Verify environment variables are set
• Check API keys are valid
• Ensure server validates credentials correctly

SSE connection drops

• Increase SSE read timeout
• Check for proxy interference
• Verify server sends keepalive events
• Review network stability

---

Related

Overview

All connection types

Agents

How agents use connections