mkinf SDK

by mkinf-io

134 stars

444 downloads

Not rated

GitHub Website

About

mkinf SDK to interact with mkinf hub MCP servers

Details

Author: mkinf-io
GitHub stars: 134
Downloads: 444
Categories: Developer Tools, AI

- Unified interface for accessing MCP-based AI agents
- Simple pip installation and Python SDK
- API-key authentication via environment variable
- Centralized hub for discovering and pulling agents
- Supports agent-specific environment variable configuration
- Compatible with LangChain chains and graphs

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name mkinf SDK

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

From the repository

Create a free account at hub.mkinf.io/signup, generate an API key from the settings page, install the SDK with pip install mkinf, find an agent on the mkinf hub, and import it using from mkinf import hub as mh with the desired agent repository name and environment variables.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mkinf sdk": {
            "mkinf": {
                "command": "uv",
                "args": [
                    "run",
                    "sync",
                    "--dev"
                ]
            }
        }
    }
}

McpServers

{
    "mkinf": {
        "command": "uv",
        "args": [
            "run",
            "sync",
            "--dev"
        ]
    }
}

# mkinf SDK ![PyPI - Version](https://img.shields.io/pypi/v/mkinf) 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](https://hub.mkinf.io/signup). <Check>During the beta period, all accounts receive unlimited free credits</Check> ## 2. Configure Your API Key 1. Go to [API Keys settings](https://hub.mkinf.io/settings/api-keys) 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: ```env .env MKINF_API_KEY=sk-org-... ``` ## 3. Install the SDK Install the mkinf SDK using pip: ```bash pip install mkinf ``` For specific versions, check the [PyPI repository](https://pypi.org/project/mkinf/). ## 4. Find an AI Agent Browse available AI Agents at [mkinf hub](https://hub.mkinf.io/) and select an agent that matches your use case ![image](https://github.com/user-attachments/assets/0ff5509f-e376-41d6-9727-29eea5221062) ## 5. Import and Use the Agent Check the "Use Agent" section of your chosen repository for import instructions ![image](https://github.com/user-attachments/assets/74e69f77-c452-4e82-82ef-824e9c48a20a) Import the agent into your code ```python 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: ```bash uv run sync --dev uv run example ```

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Install

More like this

Sentry

Github

Git

GitLab

Context 7

Sequential Thinking