Claude Desktop MCP Server

Model Context Protocol (MCP) tool to interact with Claude Desktop on macOS

Local serverstdioPython

What is the Claude Desktop MCP MCP server?

Claude desktop mcp mcp server connects Claude Desktop MCP to AI assistants that speak the Model Context Protocol. Model Context Protocol (MCP) tool to interact with Claude Desktop on macOS.

What Claude Desktop MCP does

A Model Context Protocol (MCP) server that enables Claude Code to communicate with Claude Desktop. This server allows Claude Code to send prompts to Claude Desktop and poll for responses.

Key capabilities

  • Send prompts from Claude Code to Claude Desktop
  • Automatic polling for responses with configurable timeout
  • List available conversations in Claude Desktop
  • Error handling and retry logic
  • Comprehensive logging

Tools it exposes

Once connected, the assistant can call these 11 tools directly:

  • Tool — ask
  • Parameters — { "prompt": "What is dependency injection?" }
  • description — What changes to review (e.g., "authentication fix")
  • polling_interval — How often to check for response (default: 1.5s)
  • timeout — Maximum wait time for response (default: 30s)
  • get_conversations — The get_conversations tool exposed by this server
  • Workarounds — 1. Use Claude's API: For programmatic access to responses, consider using Claude's API directly instead of desktop automation 2. Manual verification
  • Setup — 1. Copy the example command to your Claude Commands directory: bash cp examples/claude-peer-review.md ~/.claude/commands/
  • Usage — The peer review command accepts up to 3 arguments: - description: What changes to review (e.g., "authentication fix") - polling_interval: How often to
  • Linting — The Linting tool exposed by this server
  • Tools — The Tools tool exposed by this server

Installing the claude desktop mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Configuration

The server reads 2 environment variables: SKIP_CLAUDE_POLLING, LOG_LEVEL. Keep credentials in your client's env block or a secrets manager rather than committing them.

Where it fits

File and storage servers are what separate an assistant that talks about your documents from one that actually works with them. Claude Desktop MCP sits in that group, and the shape of its toolset — Tool, Parameters, description among others — tells you what it is really for. Worth comparing against the other file systems servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • With 11 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Claude Desktop MCP.
  • Maintained by dpaluy, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the claude desktop mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
Toolask
Parameters{ "prompt": "What is dependency injection?" }
descriptionWhat changes to review (e.g., "authentication fix")
polling_intervalHow often to check for response (default: 1.5s)
timeoutMaximum wait time for response (default: 30s)
get_conversationsThe get_conversations tool exposed by this server.
Workarounds1. **Use Claude's API**: For programmatic access to responses, consider using Claude's API directly instead of desktop automation 2. **Manual verification**: After sending a prompt, manually check the Claude Desktop wind
Setup1. Copy the example command to your Claude Commands directory: bash cp examples/claude-peer-review.md ~/.claude/commands/
UsageThe peer review command accepts up to 3 arguments: - **description**: What changes to review (e.g., "authentication fix") - **polling_interval**: How often to check for response (default: 1.5s) - **timeout**: Maximum wai
LintingThe Linting tool exposed by this server.
ToolsThe Tools tool exposed by this server.

How to install the Claude Desktop MCP MCP server

{
  "mcpServers": {
    "claude-desktop": {
      "command": "npx",
      "args": ["mcp-claude-desktop"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SKIP_CLAUDE_POLLINGConfiguration value read at startup.Optional
LOG_LEVELConfiguration value read at startup.Optional

Example prompts to try

  • Use Claude Desktop MCP to Tool.
  • Use Claude Desktop MCP to Parameters.
  • Use Claude Desktop MCP to description.

Frequently asked questions

It connects Claude Desktop MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 11 tools (Tool, Parameters, description, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Claude Desktop MCP directly.