πŸŽ’ Campus Lost & Found MCP Server

by utkarshagawade17

230 downloads
Not rated
GitHub

About

Modular CLI-based MCP server to manage campus lost & found items using Claude Desktop.

Details

Author
utkarshagawade17
Downloads
230
Categories
Other

- Report lost or found items via text description
- View complete lists of reported items
- Retrieve the latest lost or found item
- Generate a summary prompt for Claude to reason about
- Persistent storage using local text files
- Works seamlessly with Claude Desktop (Anthropic)

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name πŸŽ’ Campus Lost & Found MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, ensure Python 3.11+ is installed, run uv init . and uv add "mcp[cli]", then start the server with uv run main.py. For Claude Desktop integration, add the server definition to claude_desktop_config.json with the command uv --directory /path/to/CampusLostFoundMCP run main.py. Once connected, call the provided tool functions (e.g., report_lost("wallet near cafeteria"), show_lost(), summary_prompt()) directly inside Claude Desktop.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "\ud83c\udf92 campus lost & found mcp server": {
            "Campus Lost & Found": {
                "command": "uv",
                "args": [
                    "--directory",
                    "/absolute/path/to/CampusLostFoundMCP",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

McpServers

{
    "Campus Lost & Found": {
        "command": "uv",
        "args": [
            "--directory",
            "/absolute/path/to/CampusLostFoundMCP",
            "run",
            "main.py"
        ]
    }
}

πŸŽ’ Campus Lost & Found MCP Server

A Claude Desktop-compatible MCP (Model Context Protocol) server that lets users report, track, and summarize lost and found items on campus via a simple CLI or LLM interface. ---

πŸš€ Features

- Report lost or found items - View lists of reported items - Fetch the latest lost/found item - Generate a summary prompt for Claude to reason about - Persistent storage using local text files - Works seamlessly with Claude Desktop (Anthropic) ---

πŸ“ Project Structure

CampusLostFoundMCP/ β”œβ”€β”€ main.py # MCP server definition using FastMCP β”œβ”€β”€ lost.txt # Stores lost item entries (auto-created) β”œβ”€β”€ found.txt # Stores found item entries (auto-created) β”œβ”€β”€ pyproject.toml # uv/mcp environment config β”œβ”€β”€ uv.lock # Dependency lock file └── README.md ---

πŸ§ͺ Tool Functions

These can be called directly inside Claude Desktop: ``python report_lost("wallet near cafeteria") report_found("blue bottle in gym") show_lost() show_found() latest_lost() latest_found() summary_prompt() ` πŸ› οΈ Setup Instructions 1. Clone the repository: git clone https://github.com/<your-username>/CampusLostFoundMCP.git cd CampusLostFoundMCP 2. Ensure Python 3.11+ is installed 3. Install dependencies: uv init . uv add "mcp[cli]" 4. Run the server: uv run main.py 🧩 Claude Desktop Integration Add the following to your claude_desktop_config.json: { "mcpServers": { "Campus Lost & Found": { "command": "uv", "args": [ "--directory", "/absolute/path/to/CampusLostFoundMCP", "run", "main.py" ] } } } ` πŸ“¬ Future Enhancements Category filtering (e.g., electronics, books) Date-based search SQLite or cloud storage support Slack or email notifications
No reviews yet β€” be the first

Sign in to leave a review

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

Email sign in

No reviews posted yet.