mcpField
M
Mcp Wecombot Server

Mcp Wecombot Server

Local
github.com/gotoolkitsCommunication36Updated 92w ago
Repository

About Mcp Wecombot Server

mcp-wecombot-server is an MCP server that sends different message types to a WeCom group robot. It suits users who want an AI assistant to post notifications into WeCom group chats.

Key features

  1. 01Send text messages
  2. 02Send Markdown messages
  3. 03Send image messages
  4. 04Send news and template card messages
  5. 05Upload files to WeCom

Use cases

  1. 01Posting status notifications to a team group from an AI assistant
  2. 02Pushing Markdown-formatted reports to a WeCom group
  3. 03Sharing links and images through news messages

MCP support

This project is an MCP server that exposes tools such as send_text, send_markdown, send_image, send_news, send_template_card and upload_file to MCP clients.

Configuration

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

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

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@smithery/cli

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-wecombot-server

smithery badge

An MCP server application that sends various types of messages to the WeCom group robot.

Installation
Installing via Smithery

To install mcp-wecombot-server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @gotoolkits/mcp-wecombot-server --client claude-desktop
Manual Installation
# clone the repo and build
$ git clone https://github.com/gotoolkits/mcp-wecombot-server.git
$ cd mcp-wecombot-server && make build
$ sudo ln -s $PWD/dist/mcp-wecombot-server_xxx_xxxx /usr/local/bin/mcp-wecombot-server

# "$PWD/dist/mcp-wecombot-server_xxx_xxxx" replace with the actual binary file name

#You can also download and use the pre-compiled release binary package.
Configuration
{
  "mcpServers": {
    "mcp-wecombot-server": {
      "command": "mcp-wecombot-server",
      "env": {
        "WECOM_BOT_WEBHOOK_KEY": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxx"
      }
    }
  }
}
Usage
  • send_text

Send a text message to WeCom group

  • send_markdown

Send a markdown message to WeCom group

  • send_image

Send an image message to WeCom group

  • send_news

Send a news message to WeCom group,a news include title,description,url,picurl

  • send_template_card

Send a template card message to WeCom group

  • upload_file

Upload a file to WeCom

Samples

> prompt: 给我在WeCom发送一条文本消息，消息内容为：这是一条测试消息
> prompt: 给我在WeCom发送一条markdown消息，消息内容为：# 这是一条测试 Markdown 消息
> prompt: 给我在WeCom发送一条图文消息，图文标题为：这是一条图文消息，图文描述为：这是一条图文消息，图文链接为：https://github.com/gotoolkits，图文图片为：https://img-blog.csdnimg.cn/fcc22710385e4edabccf2451d5f64a99.jpeg

> Send me a text message on WeCom with the content: This is a test message.
> Send me a Markdown message on WeCom with the content: # This is a test Markdown message
> Send me a graphic message on WeCom with the title: This is a graphic message, the description: This is a graphic message, the link: https://github.com/gotoolkits, and the image: https://img-blog.csdnimg.cn/fcc22710385e4edabccf2451d5f64a99.jpeg
WeCom Robot

WeCom group robot configuration guide can be referred to: https://developer.work.weixin.qq.com/document/path/91770

WECOM_BOT_WEBHOOK_KEY is the robot webhook key
For example： https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=693axxx6-7aoc-4bc4-97a0-0ec2sifa5aaa
“693axxx6-7aoc-4bc4-97a0-0ec2sifa5aaa” is your own WECOM_BOT_WEBHOOK_KEY

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.