Model Context Protocol (MCP)
The Model Context Protocol (MCP) is a standard for extending Saarthi's capabilities by connecting to external tools and services. MCP servers provide additional tools and resources that help Saarthi accomplish tasks beyond its built-in capabilities, such as accessing databases, custom APIs, and specialized functionality.
MCP Documentation
This documentation is organized into several sections:
-
Using MCP in Saarthi - Comprehensive guide to configuring, enabling, and managing MCP servers with Saarthi. Includes server settings, tool approval, and troubleshooting.
-
What is MCP? - Clear explanation of the Model Context Protocol, its client-server architecture, and how it enables AI systems to interact with external tools.
-
STDIO, Streamable HTTP & SSE Transports - Detailed comparison of local (STDIO) and remote (Streamable HTTP & legacy SSE) transport mechanisms with deployment considerations for each approach.
-
MCP vs API - Analysis of the fundamental distinction between MCP and REST APIs, explaining how they operate at different layers of abstraction for AI systems.
-
Recommended MCP Servers - Curated list of tested and recommended MCP servers for Saarthi, including a setup guide for Context7.