mcpField
R
Reference Configurations for Claude Desktop MCP

Reference Configurations for Claude Desktop MCP

Local
github.com/bcdennisDeveloper Tools0Updated 77w ago

About Reference Configurations for Claude Desktop MCP

This repository collects reference configurations for connecting Claude Desktop to MCP servers in several Windows setups. It demonstrates connections to a JetBrains IDE and servers running in Docker or WSL.

Key features

  1. 01JetBrains connection example on Windows
  2. 02Docker server connection from Windows
  3. 03Docker server connection in WSL
  4. 04uvx server connection in WSL

Use cases

  1. 01Configure Claude Desktop to connect to a JetBrains IDE
  2. 02Connect a Windows client to a Dockerized MCP server
  3. 03Connect to a server running in WSL
  4. 04Adapt sample MCP settings for different host setups

MCP support

It provides sample MCP client configuration for Claude Desktop, illustrating how to launch or reach MCP servers across Windows, Docker, and WSL setups.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Reference Configurations for Claude Desktop MCP

Connecting Claude Desktop to Jetbrains on Windows Host with node installed in Windows

  "jetbrains": {
      "env": {
          "IDE_PORT": "58682"
      },
      "command": "npx",
      "args": [
          "-y",
          "@jetbrains/mcp-proxy"
      ]
  },
  1. Install MCP Server plugin first
  2. Go to Settings -> Debugger -> Allow External Connections
  3. Update the port to match the config. Note, Jetbrains changes ports every launch (it seems). Editing the Claude config to update the port requires the desktop app to be exited and reopened. Jetbrains IDE's don't, so I usually update Jetbrains to match the Claude config instead of vice versa.

Connecting Claude (in Windows Host) to a dockerized MCP Server (running in Windows Host)

    "github": {
        "command": "docker",
        "args": [
            "run",
            "-i",
            "--rm",
            "-e",
            "GITHUB_PERSONAL_ACCESS_TOKEN",
            "ghcr.io/github/github-mcp-server"
        ],
        "env": {
            "GITHUB_PERSONAL_ACCESS_TOKEN": "<<YOUR TOKEN>>"
        }

Connecting Claude Desktop (in Windows Host) to dockerized MCP Server (running in WSL)

    "filesystem": {
        "command": "wsl.exe",
        "args": [
            "docker",
            "run",
            "-i",
            "--rm",
            "--mount",
            "type=bind,src=<<desired directory>>,dst=/projects",
            "mcp/filesystem",
            "/projects"
        ]
    }

Connecting Claude Desktop (in Windows Host) to uvx packaged MCP Server (running in WSL)

    "git": {
        "command": "wsl.exe",
        "args": [
            "bash",
            "-c",
            "<<full path to uvx>> mcp-server-git --repository <<path to your repo>>"
        ]
    },

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.