Skip to main content

​
MCP

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

​
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

FieldDescriptionRequired
NameConnection display nameYes
PrefixTool name prefixYes
URLMCP server endpointYes
TimeoutConnection timeout (seconds)No (default: 5)
SSE Read TimeoutEvent stream timeout (seconds)No (default: 30)
Environment VariablesKey-value pairs for configurationNo

​
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

  • Verify MCP server is running
  • Check network connectivity
  • Increase timeout values
  • Confirm firewall allows traffic
  • Verify prefix is set correctly
  • Check MCP server returns tool definitions
  • Ensure protocol version is compatible
  • Review server logs for errors
  • Verify environment variables are set
  • Check API keys are valid
  • Ensure server validates credentials correctly
  • Increase SSE read timeout
  • Check for proxy interference
  • Verify server sends keepalive events
  • Review network stability

Overview

All connection types

Agents

How agents use connections