📌Overview

Purpose: The mkinf SDK aims to provide developers with an efficient toolkit for integrating MCP servers and accessing diverse AI capabilities within their applications.

Overview: mkinf simplifies the interaction with a range of AI solutions through a unified interface, making it easier for developers to implement sophisticated AI functionalities without complex configurations.

Key Features:

Easy Integration: Allows quick setup of API keys and environment configurations, facilitating seamless integration of AI agents into projects.
Diverse AI Ecosystem: Provides access to a variety of specialized AI agents through the mkinf hub, ensuring that developers can find tools tailored to their specific needs.
Compatibility with LangChain: Currently supports integration with LangChain chains and graphs, with plans to extend compatibility to additional frameworks in the future.

mkinf SDK

The mkinf SDK is a powerful toolkit that allows you to easily integrate MCP servers into your applications. With mkinf, you can access a growing ecosystem of specialized AI capabilities through a simple, unified interface.

Getting Started

Follow these steps to start using mkinf in your projects:

1. Create a mkinf Account

Sign up for a free account at https://hub.mkinf.io/signup.
During the beta period, all accounts receive unlimited free credits.

2. Configure Your API Key

Go to https://hub.mkinf.io/settings/api-keys
Create an organization if you haven't already
Generate and copy your API key
Add the key to your project's .env file:

MKINF_API_KEY=sk-org-...

3. Install the SDK

Install the mkinf SDK using pip:

pip install mkinf

For specific versions, check the PyPI repository.

4. Find an AI Agent

Browse available AI Agents at https://hub.mkinf.io/ and select an agent that matches your use case.

5. Import and Use the Agent

Check the Use Agent section of your chosen repository for import instructions.

Import the agent into your code:

from mkinf import hub as mh

tools = mh.pull(
    ["ScrapeGraphAI/scrapegraphai"],
    env={
        "SCRAPEGRAPH_LLM_MODEL": "openai/gpt-4o-mini",
        "SCRAPEGRAPH_LLM_API_KEY": os.getenv("OPENAI_API_KEY")
    }
)

Note:
Remember to configure any required environment variables specified in the agent's documentation.

Current Limitations

Warning:
Currently, mkinf tools are compatible with LangChain chains and graphs. Support for other frameworks like CrewAI, AutoGen, and SmolAgents is coming soon.

Example

You can run the included Streamlit example to see mkinf in action:

uv run sync --dev
uv run example