🧠 mcp_server-client_EAG-S-4 - Local Setup

by devdastl

171 downloads

Not rated

GitHub

Other

Description

# 🧠 mcp_server-client_EAG-S-4 - Local Setup This repository provides a minimal implementation to set up and interact with the **MCP (Modular Computation Protocol)** locally. It consists of a **server** that exposes various computational tools and a **client** that communicates…

About

Details

Author: devdastl
Downloads: 171
Categories: Other

- 28 tools including math, string/image, and Pinta automation
- Uses uv for fast dependency management and reproducibility
- Server exposes tools that a client can invoke remotely
- Includes a ready-to-use client entry point
- Pinta automation tools for drawing rectangles, circles, and text
- Image thumbnail generation and ASCII conversion tools

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_server-client_EAG-S-4 - Local Setup

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": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

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": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

From the repository

What does this project do?

It is a minimal implementation of an MCP server and client, allowing a client to call 28 different tools hosted by the server.

What runtime or dependencies are required?

Python 3, uv package manager, and the dependencies listed in pyproject.toml. For Pinta tools, the Pinta application must be installed separately.

How do I run the client?

After setting up the environment, run python mcp_client.py from the project root. The server can be tested with mcp dev mcp_server.py.

Are there any limitations or known caveats?

Pinta automation tools require Pinta to be installed and running. Image tools like create_thumbnail need valid image file paths.

What license is this project under?

MIT License.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "\ud83e\udde0 mcp_server-client_eag-s-4 - local setup": {
            "local_mcp_server-client_EAG-S-4": {
                "command": "uv",
                "args": [
                    "venv"
                ]
            }
        }
    }
}

McpServers

{
    "local_mcp_server-client_EAG-S-4": {
        "command": "uv",
        "args": [
            "venv"
        ]
    }
}

🧠 mcp_server-client_EAG-S-4 - Local Setup

This repository provides a minimal implementation to set up and interact with the MCP (Modular Computation Protocol) locally. It consists of a server that exposes various computational tools and a client that communicates with the server to invoke those tools.

The project is managed using uv, a fast Python package manager and workflow tool.

---

📂 Project Structure

- mcp_server.py — Hosts the MCP server with 28 tools available for interaction.
- mcp_client.py — The entry point of the project; runs a client that connects to the MCP server and calls its tools.
- pyproject.toml — Project configuration and dependencies using PEP 621.
- uv.lock — Auto-generated lockfile for reproducible installations using uv.
- token.env — Environment file that likely contains secrets or tokens.
- README.md — Project documentation."""

---

🛠️ Available Tools on the MCP Server

🔢 Math Tools

1. add(a, b) — Add two numbers
2. add_list(l) — Add all numbers in a list
3. subtract(a, b) — Subtract two numbers
4. multiply(a, b) — Multiply two numbers
5. divide(a, b) — Divide two numbers
6. power(a, b) — Raise a to the power of b
7. sqrt(a) — Square root
8. cbrt(a) — Cube root
9. factorial(a) — Factorial
10. log(a) — Natural logarithm
11. remainder(a, b) — Modulus operation
12. sin(a) — Sine
13. cos(a) — Cosine
14. tan(a) — Tangent
15. mine(a, b) — Special mining tool
16. int_list_to_exponential_sum(int_list) — Sum of exponentials of integers
17. fibonacci_numbers(n) — First n Fibonacci numbers

🧠 String/Image Tools

18. strings_to_chars_to_int(string) — Convert characters to ASCII
19. create_thumbnail(image_path) — Generate a thumbnail from an image

🖌️ Pinta Automation Tools

20. open_pinta_application() — Launch and focus Pinta
21. select_rectangle_tool()
22. select_text_tool()
23. select_circle_tool()
24. draw_rectangle(x1, y1, x2, y2)
25. write_text_inside_rectangle(text, x1, y1, x2, y2)
26. draw_circle(x1, y1, radius)
27. get_lines_of_rectangle(x1, y1, x2, y2) — Return lines from rectangle coordinates
28. get_midpoint_of_line(x1, y1, x2, y2) — Return midpoint of a line

---

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/your-username/mcp-protocol.git
cd mcp-protocol

2. Install `uv` (if not already installed)

curl -Ls https://astral.sh/uv/install.sh | sh

Verify installation:

uv --version

3. Set Up the Project Environment

uv venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
uv pip install -r pyproject.toml

> If requirements.txt doesn't exist:
>
>

> uv pip freeze > requirements.txt

>

4. Test MCP Server with GUI client

mcp dev mcp_server.py

5. Run the Client

python mcp_client.py

---

📌 Notes

- Ensure Pinta is installed if you're using Pinta-related tools.
- Image tools like create_thumbnail require valid image paths.
- mcp_client.py is the main entry point to interact with the protocol.

---

📄 License

MIT License. Feel free to fork, modify, and contribute.

---

🤝 Contributing

Pull requests are welcome. For major changes, please open an issue first.

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.

Description

About

Details

Jump to

Setting up with Highlight

From the repository

What does this project do?

What runtime or dependencies are required?

How do I run the client?

Are there any limitations or known caveats?

What license is this project under?

Claude Desktop / Cursor

McpServers

🧠 mcp_server-client_EAG-S-4 - Local Setup

📂 Project Structure

🛠️ Available Tools on the MCP Server

🔢 Math Tools

🧠 String/Image Tools

🖌️ Pinta Automation Tools

🚀 Getting Started

1. Clone the Repository

2. Install uv (if not already installed)

3. Set Up the Project Environment

4. Test MCP Server with GUI client

5. Run the Client

📌 Notes

📄 License

🤝 Contributing

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀

2. Install `uv` (if not already installed)