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.
mkinf-io/mkinf
mkinf is a Python SDK that lets an application consume MCP servers hosted on the mkinf hub without running or wiring each server itself. The workflow described in the README has four steps: create an account on hub.mkinf.io, generate an API key inside an organization, put that key into the project environment as MKINF_API_KEY, and install the package from PyPI with pip install mkinf. Once installed, the developer browses the hub for a published agent, opens its Use Agent section for import instructions, and pulls it into code. The pull call is the core of the interface: it takes a list of hub repository identifiers such as ScrapeGraphAI/scrapegraphai together with an env mapping that carries whatever configuration that particular agent requires, for example a model name and a provider API key, and it returns tool objects ready to be handed to an agent framework. Each hub entry documents the environment variables it needs, so configuration stays with the agent rather than in the SDK. The README states a clear limitation at the time of writing: the returned tools work with LangChain chains and graphs only, and support for CrewAI, AutoGen and SmolAgents is described as planned rather than available. The repository ships a Streamlit example that can be run with uv to see the integration end to end. During the stated beta period all accounts receive free credits. The project suits Python developers who already build on LangChain and want to add capabilities from a catalogue of MCP-backed agents through one dependency and one API key, instead of managing separate server processes, transports and credentials for every integration they add.
https://github.com/mkinf-io/mkinf
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.
cognitivecomputations/dolphin-mcp
Dolphin MCP is a flexible Python library and CLI tool that enables conversational interaction with multiple Model Context Protocol (MCP) servers using various large language models.
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.