Pin Wen

@OpenAgentPlatform

About Pin Wen

No overview available yet

Config

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

{
  "mcpServers": {
    "echo": {
      "transport": "stdio",
      "enabled": false,
      "command": "node",
      "args": [
        "/Users/biggo2/.dive/scripts/echo.js"
      ],
      "env": {},
      "url": null,
      "headers": null,
      "extraData": null
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Pin Wen?

Pin Wen is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities.

How to use Pin Wen?

Download the latest release for your operating system (Windows .exe, macOS .dmg, Linux .AppImage). After installation, configure MCP servers via the JSON settings in the app’s UI. You can start with the built-in echo MCP server or add custom tools like fetch, filesystem, and youtubedl by pasting their JSON configuration.

Key features of Pin Wen

Universal LLM support: ChatGPT, Anthropic, Ollama, OpenAI-compatible models
Cross-platform desktop app for Windows, MacOS, and Linux
Model Context Protocol with both stdio and SSE transport modes
Multi-language support: Traditional Chinese, Simplified Chinese, English, Spanish, Japanese, Korean
Advanced API management with multiple keys and model switching
Custom system prompts for tailored AI behavior
Built-in auto-update mechanism

Use cases of Pin Wen

Running MCP-based AI agents on your desktop with various LLMs
Experimenting with MCP tools like fetching web content, filesystem operations, or YouTube downloads
Developing and testing custom MCP servers in a local GUI environment
Switching between different LLM providers and models for comparative analysis

FAQ from Pin Wen

What LLMs does Pin Wen support?

It supports ChatGPT, Anthropic, Ollama, and any OpenAI-compatible model. Version 0.8.0 added Google Gemini and Mistral AI.

What are the system requirements?

Windows: .exe with Python and Node.js pre-installed. MacOS/Linux: .dmg or .AppImage; you need to install Python and Node.js (with npx and uvx) yourself.

How do I add MCP tools?

Open the MCP configuration panel in the app and add a JSON entry with the command, args, and enabled flag. Examples for fetch, filesystem, and youtubedl are provided in the README.

How do I connect to an external MCP server via SSE?

In the MCP settings, add a server entry with "transport": "sse" and the server’s URL.

Will upgrading to v0.8.0 preserve my old data?

No. Due to the migration from TypeScript to Python, configuration files and chat history are not automatically upgraded. You can downgrade to access old data if needed.

Frequently asked questions