Model Context Protocol (MCP)

Model Context Protocol support across OpenHands platforms

Model Context Protocol (MCP) is an open standard that allows OpenHands to communicate with external tool servers, extending the agent’s capabilities with custom tools, specialized data processing, external API access, and more. MCP is based on the open standard defined at modelcontextprotocol.io.

How MCP Works

When OpenHands starts, it:

1. Reads the MCP configuration
2. Connects to configured servers (SSE, SHTTP, or stdio)
3. Registers tools provided by these servers with the agent
4. Routes tool calls to appropriate MCP servers during execution

MCP Support Matrix

Platform	Support Level	Configuration Method	Documentation
CLI	✅ Full Support	~/.openhands/mcp.json file	CLI MCP Servers
SDK	✅ Full Support	Programmatic configuration	SDK MCP Guide
Agent Canvas	✅ Full Support	Customize > MCP Servers	Customize and Settings
OpenHands Cloud	✅ Full Support	Cloud UI settings	Cloud GUI

Platform-Specific Differences

CLI

• Configuration via ~/.openhands/mcp.json file
• Real-time status monitoring with /mcp command
• Supports all MCP transport protocols (SSE, SHTTP, stdio)
• Manual configuration required

SDK

• Programmatic configuration in code
• Full control over MCP server lifecycle
• Dynamic server registration and management
• Integration with custom tool systems

Agent Canvas

• Visual configuration through Customize > MCP Servers
• Real-time server status display
• Supports all transport protocols
• Synced to the active backend

OpenHands Cloud

• Cloud-based configuration management
• Managed MCP server hosting options
• Team-wide configuration sharing
• Enterprise security features

Getting Started with MCP

• For detailed configuration: See Customize and Settings
• For CLI usage: See CLI MCP Servers
• For SDK integration: See SDK MCP Guide
• For architecture details: See MCP Architecture