mcpField
F
FastMCP_Claude_Desktop

FastMCP_Claude_Desktop

Local
github.com/nuke66AI & Agents0Updated 84w ago
Repository

About FastMCP_Claude_Desktop

FastMCP_Claude_Desktop is a small project for trying an MCP server with Claude Desktop. Its README documents installing the MCP package, registering a server in Claude Desktop’s configuration, and using the inspector to run it.

Key features

  1. 01MCP package installation
  2. 02Claude Desktop configuration
  3. 03Server installation command
  4. 04Inspector-based server testing

Use cases

  1. 01Registering a server in Claude Desktop
  2. 02Running a server with the MCP inspector

MCP support

The project documents how to install and run an MCP server for Claude Desktop, and how to inspect it with `mcp dev server.py`.

#mcp#claude#desktop

Configuration

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

mcp.json · Universal config
{
  "mcpServers": {
    "FastMCP_Claude_Desktop": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem"
      ]
    }
  }
}
Run commandnpx -y @modelcontextprotocol/server-filesystem

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@modelcontextprotocol/server-filesystem

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

MCP playaround https://modelcontextprotocol.io/quickstart/user https://modelcontextprotocol.io/quickstart/server

pypi doco https://pypi.org/project/mcp/

Create a config file for claude desktop. File -> Settings, Developer tab, then click Edit Config. This will create a config file call claude_desktop_config.json. e.g. C:\Users\Slade\AppData\Roaming\Claude\claude_desktop_config.json

pip install mcp

Run so available in Claude desktop, this will create an entry in claude_desktop_config.json

mcp install server.py

C:\Users\Slade\AppData\Roaming\Python\Python310\Scripts\mcp.exe install server.py

or use this config file (for non uv)

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "C:\\Users\\Slade\\Downloads"
      ]
    },
    "Demo4": {
      "command": "C:\\Users\\Slade\\AppData\\Roaming\\Python\\Python310\\Scripts\\mcp",
      "args": [
          "run",
          "C:\\dev\\xFastMCP\\server.py"
      ]
    }
  }
}

img

Run inspector

mcp dev server.py

C:\Users\Slade\AppData\Roaming\Python\Python310\Scripts\mcp.exe dev server.py

change LHS settings to match your working config from claude_desktop_config.json, e.g.

Command: C:\\Users\\Slade\\AppData\\Roaming\\Python\\Python310\\Scripts\\mcp
Arguments: run C:\\dev\\xFastMCP\\server.py

img

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.