Model Context Protocol (MCP)
Model Context Protocol (MCP) is an open standard that allows Faheem Code 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 Faheem Code starts, it:
- Reads the MCP configuration
- Connects to configured servers (SSE, SHTTP, or stdio)
- Registers tools provided by these servers with the agent
- Routes tool calls to appropriate MCP servers during execution
MCP support matrix
| Platform | Support Level | Configuration Method | Documentation |
|---|---|---|---|
| CLI | ✅ Full Support | ~/.faheem-code/mcp.json file | CLI MCP Servers |
| SDK | ✅ Full Support | Programmatic configuration | SDK MCP Guide |
| Local GUI | ✅ Full Support | Settings UI + config files | Local GUI |
| Faheem Code Cloud | ✅ Full Support | Cloud UI settings | Cloud GUI |
Platform-specific differences
- Configuration via
~/.faheem-code/mcp.jsonfile - Real-time status monitoring with
/mcpcommand - Supports all MCP transport protocols (SSE, SHTTP, stdio)
- Manual configuration required
- Programmatic configuration in code
- Full control over MCP server lifecycle
- Dynamic server registration and management
- Integration with custom tool systems
- Visual configuration through Settings UI
- File-based configuration backup
- Real-time server status display
- Supports all transport protocols
- Cloud-based configuration management
- Managed MCP server hosting options
- Team-wide configuration sharing
- Enterprise security features
Getting started with MCP
- For detailed configuration: See MCP Settings
- For CLI usage: See CLI MCP Servers
- For SDK integration: See SDK MCP Guide
- For architecture details: See MCP Architecture