mark3labs/mcp-go
Mcp Go
mcp-go is a Go implementation of the Model Context Protocol (MCP) providing an SDK and framework for building servers that connect large language model applications to external tools and data sources. It serves as a developer kit for implementing bidirectional communication and structured data exchange between AI clients and servers.
The framework enables the creation of executable tools with structured output schemas, reusable prompt templates, and data resource exposure via URI templates. It supports multiple transport layers, including stdio, HTTP, and Server-Sent Events, using a transport-agnostic message bus to decouple protocol logic from the communication channel.
The library includes capabilities for session-based context tracking, capability filtering, and handler middleware for logging and error recovery. It further provides observability through request tracing and lifecycle hooks, as well as security configurations for CORS and OAuth metadata exposure.
Features
- Model Context Protocol - Implements the standardized Model Context Protocol to connect AI models with local data and external tools.
- Model Context Protocol Implementations - Implements the Model Context Protocol (MCP) to standardize communication between AI models and external tools.
- Agent Context Management - Manages agent context by serving static files and dynamic API data as resources for language models.
- LLM Tooling Integrations - Provides a framework for creating executable functions and tools that language models can trigger in external systems.
- MCP Servers - Implements the server side of the Model Context Protocol to expose tools and data via stdio, SSE, or HTTP.
- Resource Exposure - Exposes read-only static files and dynamic data as resources to serve as context for AI models.
- Transport Layer Connectivity - Supports multiple communication channels including stdio, HTTP, and SSE for reliable connectivity.
- Model Context Protocol Servers - Provides a framework for creating executable functions that allow language models to perform computations and trigger side effects.
- Bidirectional Protocol Communication - Enables bidirectional exchange of requests and notifications between servers and clients using HTTP POST and Server-Sent Events.
- JSON-RPC Implementations - Implements the JSON-RPC protocol to standardize the exchange of requests and responses between AI clients and servers.
- Go SDKs - Provides a comprehensive Go developer kit for implementing bidirectional communication between AI clients and servers.
- Conversation Context Tracking - Maintains unique client state to deliver targeted notifications and filtered capability lists based on session context.
- Middleware Extensions - Provides middleware extensions to intercept and modify protocol communication for logging and error recovery.
- Structured Tool Outputs - Returns complex data types using defined schemas to ensure precisely formatted output for language models.
- Prompt Templates - Provides capabilities to define reusable prompt templates with system instructions and arguments for guiding language models.
- AI Tool Schemas - Uses structured metadata to define precise function arguments and return types for language model execution.
- Dynamic Resource Templates - Maps unique resource identifiers to dynamic data generators using URI templates to provide model context.
- Client Session Management - Maintains unique states for connected clients to enable targeted notifications and personalized configurations.
- Protocol-Agnostic Transport Layers - Decouples protocol logic from underlying communication channels using a transport-agnostic message bus.
- Asynchronous Task Execution - Implements non-blocking background task execution for tools with polling mechanisms for result retrieval.
- Task Status Polling - Provides a polling mechanism for clients to retrieve results from long-running background operations.
- AI Protocol Observability - Tracks request lifecycles and tool executions with telemetry and spans to debug client-server interactions.
- Request Tracing - Tracks requests and tool executions using spans and attributes for performance debugging.
- AI Agent Frameworks - SDK for developing Model Context Protocol clients and servers.
- AI and Machine Learning - Go implementation of the Model Context Protocol.
- AI & Machine Learning - Implementation of the Model Context Protocol for Go.
- Development and Debugging Tools - Go language implementation for building efficient MCP servers.
