README.md

by romanshablio

119 downloads
Not rated
GitHub

About

Lightweight Python HTTP service that searches local files by name and returns JSON results for tools such as Cline.

Details

Author
romanshablio
Downloads
119
Categories
Knowledge Base

- Runs locally on the user's computer.
- Exposes a simple HTTP search endpoint.
- Searches files by query and returns JSON results.
- Saves the latest search output to search_results.json.
- Can be connected to Cline in VS Code.

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 README.md
    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, start the server with python mcp_server.py --port 8080, and configure Cline in VS Code by copying the appropriate configuration into cline_config.json and restarting Cline. The server exposes a single HTTP endpoint /search that accepts a query parameter.

Claude Desktop / Cursor

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

{
    "mcpServers": {
        "readme.md": {
            "mcp-server-romanshablio": {
                "command": "python",
                "args": [
                    "mcp_server.py",
                    "--port",
                    "8080"
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server-romanshablio": {
        "command": "python",
        "args": [
            "mcp_server.py",
            "--port",
            "8080"
        ]
    }
}

MCP File Finder Server

MCP File Finder Server is a small Python service for searching files by name on a local computer and returning results as JSON.

The project was created as a local MCP-style helper that can be connected to tools such as Cline in VS Code. It exposes an HTTP endpoint for search requests and saves the latest search results to search_results.json.

Features

- Runs locally on the user's computer.
- Exposes a simple HTTP search endpoint.
- Searches files by query.
- Returns results in JSON format.
- Saves search output to search_results.json.
- Can be connected to Cline in VS Code through configuration.

Installation and Running

1. Clone the repository.

   git clone <repository-url>
   cd <repository-folder>
   

2. Start the MCP server.

   python mcp_server.py --port 8080
   

3. Configure Cline in VS Code.

- Open cline_config.json.
- Copy the configuration into Cline.
- Restart Cline.

Testing

Send a GET request:

curl "http://localhost:8080/search?query=example"

The server returns a JSON response with matching files.

How It Works

1. Start the server.
2. Send a search request through curl, a browser, or another tool.
3. The server scans the local computer for matching filenames.
4. Matching results are saved to search_results.json.
5. The response is returned as JSON.

Purpose

The main idea is to automate local file search and make it available to external tools. The server can later be connected to a GUI, an AI assistant, or another program that needs local file search through a simple API.

No reviews yet — 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.