modelcontextprotocol/python-sdk
The official Python SDK for the Model Context Protocol (MCP) enabling developers to build standardized MCP servers and clients for LLM context and interaction.
cognitivecomputations/dolphin-mcp
Dolphin MCP is a versatile Python library and command-line interface tool designed to interact with Model Context Protocol (MCP) servers using any large language model (LLM). It enables users to query and manipulate data conversationally by connecting to multiple MCP servers simultaneously. The tool supports various LLM providers including OpenAI, Anthropic, Ollama, and LMStudio, allowing seamless integration of their models for natural language processing tasks. The project features a modular architecture that cleanly separates provider-specific modules, making it easy to extend and maintain. Users can discover and utilize tools provided by MCP servers automatically, facilitating dynamic interaction with external data sources. Configuration is flexible, supporting JSON files for defining MCP servers and environment variables for securely storing API keys. Dolphin MCP offers both a Python library for programmatic access and a command-line interface for direct user interaction. The CLI supports interactive chat mode, quiet mode, and logging of LLM interactions, providing a comprehensive user experience. The library is installable via pip and includes detailed documentation and usage examples. The project also includes a demo setup with a sample SQLite database to illustrate its capabilities. It demonstrates how to connect to multiple MCP servers, list and call their tools, and process results in a user-friendly manner. Dolphin MCP is ideal for developers and researchers looking to leverage MCP servers and large language models for conversational data access and tool integration.
https://github.com/cognitivecomputations/dolphin-mcp
Also in Python
PrefectHQ/fastmcp
FastMCP offers a Pythonic framework for developing and interacting with Model Context Protocol (MCP) servers and clients, facilitating efficient communication with LLMs.
tadata-org/fastapi_mcp
FastAPI-MCP is a tool that exposes FastAPI endpoints as Model Context Protocol (MCP) tools with built-in authentication, preserving schemas and documentation, and supporting flexible deployment using FastAPI's native ASGI interface.
mcp-use/mcp-use
mcp-use is an open-source client library that enables easy connection of any tool-capable LLM to MCP servers for building custom agents with diverse tool access.
golf-mcp/golf
Golf is a production-ready framework for building, deploying, and scaling secure MCP servers that power AI agents, featuring automatic component discovery, built-in authentication, observability, debugging, telemetry, and runtime management.
rectalogic/langchain-mcp
langchain-mcp provides Model Context Protocol (MCP) tool support for the LangChain framework, enabling integration of MCP-compliant tools to enhance language model applications.
googleapis/mcp-toolbox-sdk-python
Google's Python SDK collection for MCP Toolbox, loading tools defined in a Toolbox server as plain Python functions or as ready-made tools for ADK, LangChain, LangGraph and LlamaIndex.
mkinf-io/mkinf
Python SDK that pulls hosted MCP servers from the mkinf hub and exposes them as LangChain-compatible tools through a single unified interface.