MCP Link: Empowering AI Agents with Real-World Tools 🌐🤖

by 10210wkkw

399 downloads

Not rated

GitHub

AI
Finance

About

Let AI agents like ChatGPT & Claude use real-world local/remote tools you approve via browser extension + optional MCP server

Details

Author: 10210wkkw
Downloads: 399
Categories: AI, Finance

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 MCP Link: Empowering AI Agents with Real-World Tools 🌐🤖

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": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

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": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

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": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

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": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

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": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

From the repository

Install the browser extension for Chrome, Firefox, or Safari. Optionally set up the MCP server with Docker (build image and run on port 8080). Open the extension, sign in, approve tools, and start interacting with your AI agent.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "mcp link: empowering ai agents with real-world tools \ud83c\udf10\ud83e\udd16": {
            "mcp-link-10210wkkw": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp-server",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "mcp-link-10210wkkw": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "mcp-server",
            "."
        ]
    }
}

MCP Link: Empowering AI Agents with Real-World Tools 🌐🤖

Welcome to the MCP Link repository! This project allows AI agents like ChatGPT and Claude to utilize local and remote tools you approve. Through a browser extension and an optional MCP server, you can enhance the capabilities of your AI agents seamlessly.

1. Introduction
2. Features
3. Installation
4. Usage
5. Contributing
6. License
7. Support
8. Acknowledgments

Introduction

MCP Link serves as a bridge between AI agents and real-world tools. By using this repository, you enable your AI to interact with various applications and services that you trust. This project focuses on providing a secure and efficient way to integrate AI into your daily workflows.

The MCP Link project is built around the Model Context Protocol (MCP), which facilitates seamless communication between AI models and external tools. With this, you can enhance your AI's functionality, making it a more powerful assistant in various tasks.

Features

- Browser Extensions: Available for Chrome, Firefox, and Safari, allowing easy integration with your preferred browser.
- MCP Server: An optional server that can enhance communication and functionality.
- Tool Approval System: Control which tools your AI agents can access, ensuring security and privacy.
- Semantic Search: Use advanced search techniques to find relevant information quickly.
- Docker Sandbox: Isolate your tools and agents for secure testing and deployment.
- AI Automation: Automate repetitive tasks with the help of AI.
- Integration with Various Tools: Connect with a wide range of applications, enhancing your AI's capabilities.

Installation

To get started with MCP Link, follow these steps:

Prerequisites

- Ensure you have a compatible browser (Chrome, Firefox, or Safari).
- For the MCP server, you will need Docker installed on your machine.

Steps

1. Clone the Repository:

   git clone https://github.com/10210wkkw/mcp-link.git

   cd mcp-link

2. Install Browser Extension:
- For Chrome, visit the Chrome Web Store and search for "MCP Link".
- For Firefox, find it on the Firefox Add-ons site.
- For Safari, check the App Store.

3. Set Up MCP Server (Optional):
If you choose to use the MCP server, run the following commands:

   docker build -t mcp-server .

   docker run -p 8080:8080 mcp-server

4. Download and Execute Releases:
Visit the Releases section to download the latest version of the software. Follow the instructions provided in the release notes to execute it.

Usage

Once you have installed the browser extension and set up the MCP server, you can start using MCP Link.

Setting Up Your AI Agent

1. Open the browser extension.
2. Sign in with your credentials.
3. Approve the tools you want your AI agent to access.
4. Start interacting with your AI agent, providing it with tasks that involve the approved tools.

Example Use Cases

- AI-Assisted Research: Use your AI agent to gather data from various sources and compile reports.
- Automated Customer Support: Set up your AI to handle customer inquiries using approved tools.
- Personal Productivity: Automate scheduling, reminders, and task management through your AI agent.

Contributing

We welcome contributions to MCP Link! If you want to help improve the project, follow these steps:

1. Fork the Repository: Click on the "Fork" button at the top right corner of the page.
2. Create a New Branch:

   git checkout -b feature/YourFeature

3. Make Your Changes: Edit files as needed.
4. Commit Your Changes:

   git commit -m "Add your message here"

5. Push to Your Branch:

   git push origin feature/YourFeature

6. Open a Pull Request: Go to the original repository and click on "New Pull Request".

License

This project is licensed under the MIT License. See the LICENSE file for details.

Support

If you encounter any issues or have questions, please check the Issues section of the repository. You can also reach out via email at support@mcp-link.com.

Acknowledgments

We would like to thank all contributors and users who have supported this project. Your feedback and contributions help us improve MCP Link and make it a better tool for everyone.

---

Thank you for exploring MCP Link! We hope you find it valuable for enhancing your AI agents with real-world tools. For the latest updates and releases, please visit the Releases section.

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

MCP Link: Empowering AI Agents with Real-World Tools 🌐🤖

Table of Contents

Introduction

Features

Installation

Prerequisites

Steps

Usage

Setting Up Your AI Agent

Example Use Cases

Contributing

License

Support

Acknowledgments

Install

More like this

Context 7

1Panel

🔎 GPT Researcher

Serena

FastMCP v2 🚀

MaxKB