Skip to main content
Connect your agents to external systems and services through the Model Context Protocol. MCP enables seamless integration with databases, APIs, file systems, and third-party platforms, giving your agents access to real-world data and capabilities.

​
What is MCP?

The Model Context Protocol is a standardized way for AI agents to interact with external systems. MCP servers act as bridges between your agent and various services, enabling your AI to:
  • Access external data sources - Connect to databases, file systems, cloud storage, and APIs
  • Integrate with platforms - Work with GitHub, Slack, Google Drive, Notion, and more
  • Execute system operations - Run commands, query databases, manipulate files
  • Maintain context - Keep consistent access to resources across conversations
Think of MCP as a universal adapter that lets your agent plug into virtually any service or data source through a standardized interface.

​
Setup MCP Tab View

1

Navigate to MCP Tab View

Go to Tools & MCP Page to view and manage your connected servers.MCP servers interface
2

Add a New Server

Click Add Server and configure your MCP connection:Add MCP server form
3

Enable for Projects

Once added, enable the MCP server for specific projects where you want your agent to have access to its capabilities.
4

Test Your Connection

Start a conversation with your agent and ask it to use the connected service:Testing MCP in chatYour agent will automatically use MCP tools when relevant to the conversation.

​
Using MCP Servers

​
Via UI

1

Connect Servers

Navigate to Tools & MCP Page and add the servers you need.
2

Enable for Projects

Select which projects should have access to each MCP server.
3

Chat Naturally

Your agent will automatically use MCP resources when they’re relevant to your conversation. No special commands needed.
4

Monitor Activity

Use the Sources tab to see which MCP servers were called and what data was accessed.

​
Via API

You can programmatically manage MCP servers through the API. Check the MCP API Reference for detailed documentation on:
  • Adding and removing servers
  • Managing server configurations
  • Enabling servers for projects
  • Monitoring server status
The AI automatically determines when to use MCP resources based on the conversation context and available server capabilities.