Advertise
MCP.so
Sign In

Project Description MCP Server

@michalpawlik93

Repository

Basic information

Category

Other

License

MIT license

Transports

stdio

Author

michalpawlik93

About Project Description MCP Server

No overview available yet

#mcplocalserver#middleware#node-js

Project Description MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcpLocalServer": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "build/index.js"
      ]
    }
  }
}

Project Description MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is MCP Server?

MCP Server is a Node.js application for Windows that acts as a local middleware for seamless communication between LLM-based tools (e.g., Copilot Agents) and local files or prompts. It is designed to run alongside an IDE like Visual Studio Code or Visual Studio.

How to use MCP Server?

Install dependencies (npm install), configure the environment variables GUIDE_FILES_DIR and PROMPT_DIR in a .env file, build the project (npm run build), then run it with npx @modelcontextprotocol/inspector build/index.js for browser testing. For integration with Visual Studio Code, create a .vscode/mcp.json file pointing to the built index.js and follow the official MCP documentation.

Key features of MCP Server

  • Three built-in tools: ListAvailableFilesTool, ListPromptsTool, ReadLocalFileTool
  • Supports custom guide files (prefix guide_) and prompt files (prefix prompt_)
  • Works with the @modelcontextprotocol/sdk and can be tested via the Inspector
  • Designed for local, offline use with IDEs like VS Code
  • Allows developers to create and register custom tools in TypeScript

Use cases of MCP Server

  • Provide LLM agents with local documentation and guide files for code generation
  • Use custom prompt files to control Copilot Agents’ behavior and output format
  • Enable an agent to read specific local files (e.g., coding standards) before writing code
  • Serve as a middleware for Copilot for Visual Studio Code to interact with project-specific resources

Frequently asked questions

1

What are the required environment variables?

Set `GUIDE_FILES_DIR` to the folder containing your guide files and `PROMPT_DIR` to the folder containing your prompt files. Use double backslashes in paths (e.g., `C:\\path\\to\\data`).

2

How do I integrate MCP Server with Visual Studio Code?

Create a `.vscode/mcp.json` file with a `"servers"` entry that specifies `"node"` as the command and the full path to `build/index.js` as the argument. Then use `Ctrl+Shift+P` and run `MCP: List Servers` to start the server.

3

What file types are supported?

Only `.txt` files are supported. Guide files must have the prefix `guide_` and prompt files must have the prefix `prompt_`.

4

How can I add a custom tool?

Create a new `.ts` file in the `src/tools` directory, register the tool in `localMcpServer.ts`, then rebuild the project with `npm run build`.

5

How do I test MCP Server?

Run `npx @modelcontextprotocol/inspector build/index.js` to start the Inspector tool, which allows you to test the server in a web browser.

Comments

More Other MCP servers

Sequential Thinking

modelcontextprotocol

Model Context Protocol Servers

88.2K

ICSS

chokcoco

不止于 CSS

20.7K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

Advertise