mcpField
M
mkinf SDK

mkinf SDK

Local
mkinf.ioDeveloper Tools131Updated 84w ago
RepositoryVisit website

About mkinf SDK

The mkinf SDK is a Python toolkit for importing MCP servers from the mkinf hub into applications through a unified interface. It suits developers who build LangChain chains or graphs and want to reuse published agents. Currently only LangChain is supported, with other frameworks planned.

Key features

  1. 01API key authentication to the mkinf hub
  2. 02Import agent tools with a pull method
  3. 03Pass environment variables to imported agents
  4. 04Includes a Streamlit example application

Use cases

  1. 01Calling hub-hosted MCP servers from LangChain applications
  2. 02Integrating web scraping agents such as ScrapeGraphAI into existing projects

MCP support

The SDK pulls MCP servers from the mkinf hub and makes their tools available inside an application, acting as a client-side integration layer.

#python#sdk#ai#mcp#llm#modelcontextprotocol

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mkinf SDK

PyPI - Version

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 hub.mkinf.io/signup. During the beta period, all accounts receive unlimited free credits

2. Configure Your API Key

  1. Go to API Keys settings
  2. Create an organization if you haven't already
  3. Generate and copy your API key
  4. 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 mkinf hub and select an agent that matches your use case

image

5. Import and Use the Agent

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

image

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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.