WeCom MCP Server
Enables AI agents to send messages, query contacts, and manage message history for WeCom (WeChat Work) self-built applications via the Model Context Protocol.
README
WeCom MCP Server

A Python-based MCP (Model Context Protocol) Server for WeCom (WeChat Work / ä¼äøå¾®äæ”) self-built applications.
Provides a standard set of MCP tools that enable AI Agents (e.g., Trae Work, Claude Desktop) to send messages to WeCom users/departments, query contacts, receive and store messages, and more.
š äøęē (Chinese)
⨠Features
Core Capabilities
- šØ Message Sending: Text, Markdown, generic message bodies, file sending, and
@allmass messaging - š Contact Lookup: Quickly find UserIDs by member name, or batch-retrieve members by department
- š„ Message Reception: In HTTP mode, automatically listens for WeCom callbacks and persists received messages to SQLite in real time
- š History Query: Query historical messages by time, type, sender, keywords, and more
- šļø File Management: Received images/voice/video/files are automatically downloaded to local disk with metadata stored in the database
Technical Highlights
- Pure-Python AES-256-CBC: No dependency on the
cryptographylibrary, avoiding native compilation issues on certain platforms - Multiple Transport Support:
stdio(single Agent),streamable-http(shared by multiple Agents),sse(legacy compatibility) - SQLite Yearly Partitioning: Automatically splits data tables by calendar year to prevent single-table bloat
- Managed by
uv: Ultra-fast package manager and virtual environment
š ļø MCP Tool List
Universal Tools (Stdio & HTTP/SSE)
| Tool Name | Description |
|---|---|
send_text_message |
Send a text message |
send_markdown_message |
Send a Markdown message |
send_message |
Send any type of message (text/markdown/news, etc.) |
send_file_message |
Send a local file (auto-upload) |
mass_send_message |
Mass message all members in the app's visible scope (@all) |
lookup_user_id |
Find UserID by member name |
list_users_by_department |
List all members in a department (including sub-departments) |
check_config |
Check current WeCom configuration status |
HTTP/SSE Exclusive Tools
| Tool Name | Description |
|---|---|
health_check |
Health check (Webhook status, database status, etc.) |
search_history_messages |
Query historical messages (filter by time/type/sender/keywords) |
get_message_detail |
Get details of a single message |
get_message_file |
Get the local file path associated with a message |
list_message_years |
List years that have historical data |
get_message_stats |
Historical message statistics (by type/sender/month) |
š Quick Start
1. Requirements
- Python >= 3.14
- uv package manager
2. Installation & Configuration
# Clone the project
git clone <your-repo-url>
cd wecom-mcp-server
# Create virtual environment and install dependencies
uv sync
# Copy the environment variable template
cp .env.example .env
3. Configuration
Edit .env and fill in your WeCom self-built application credentials:
# Corp ID
WECOM_CORP_ID=ww1234567890abcdef
# Self-built App Secret
WECOM_CORP_SECRET=your_app_secret
# Self-built App AgentId (number)
WECOM_AGENT_ID=1000002
# ====== Optional ======
# Contacts Sync Secret (recommended for full-directory access)
WECOM_CONTACTS_SECRET=your_contacts_secret
# Message callback (only needed for receiving messages / history query)
WECOM_CALLBACK_TOKEN=your_callback_token
WECOM_CALLBACK_ENCODING_AES_KEY=your_aes_key_43_chars_long
# MCP service mode
# stdio: default, single-client local calls
# streamable-http: HTTP service, shared by multiple Agents
# sse: legacy SSE mode
WECOM_MCP_TRANSPORT=streamable-http
WECOM_MCP_HOST=0.0.0.0
WECOM_MCP_PORT=9000
# Data persistence directory
WECOM_DATA_DIR=data
4. Run
Mode 1: Stdio (for Trae Work)
Add to your Trae Work MCP configuration:
{
"mcpServers": {
"wecom": {
"command": "uv",
"args": ["run", "--directory", "/path/to/wecom-mcp-server", "wecom-mcp-server"]
}
}
}
Mode 2: HTTP Service (shared by multiple Agents)
# Run in foreground
uv run wecom-mcp-server --transport streamable-http --host 0.0.0.0 --port 9000
# Or use .env configuration
WECOM_MCP_TRANSPORT=streamable-http WECOM_MCP_PORT=9000 uv run wecom-mcp-server
Callers interact with the MCP Server via HTTP:
curl -X POST http://localhost:9000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "send_text_message", "arguments": {"to_user": "zhangsan", "content": "Hello!"}}}'
āļø Supervisor Deployment
To keep the service running in the background, use supervisord.
Config file: /usr/local/etc/supervisor.d/wecom-mcp-server.conf
[program:wecom-mcp-server]
command=/usr/local/bin/uv run wecom-mcp-server --transport streamable-http --host 0.0.0.0 --port 9000
directory=/path/to/wecom-mcp-server
user=your_username
autostart=true
autorestart=true
startretries=3
stopasgroup=true
killasgroup=true
stderr_logfile=/path/to/logs/wecom-mcp-server.err.log
stdout_logfile=/path/to/logs/wecom-mcp-server.out.log
environment=LANG="en_US.UTF-8",PATH="/usr/local/bin:/usr/bin:/bin"
Common commands:
supervisorctl reread # Reload configuration
supervisorctl update # Update process groups
supervisorctl status # View all service statuses
supervisorctl restart wecom-mcp-server # Restart service
š Project Structure
wecom-mcp-server/
āāā src/
ā āāā wecom_mcp_server/
ā āāā __init__.py
ā āāā server.py # MCP Server entry point, tool registration
ā āāā config.py # Configuration management (pydantic-settings)
ā āāā aes.py # Pure-Python AES-256-CBC implementation
ā āāā crypto.py # WeCom message encryption/decryption logic
ā āāā wecom_client.py # WeCom API async client
ā āāā webhook.py # Message reception webhook service
ā āāā storage.py # SQLite message persistence & file management
āāā .env.example # Environment variable example
āāā pyproject.toml # Project dependencies & build config
āāā README.md # This document
š Configuration Notes
WeCom App Permissions
- Basic Sending Permission: Create a self-built app in the WeCom admin backend and obtain
CorpID,Secret, andAgentId. - Contact Reading Permission (optional): Enable
API Interface Syncin "Management Tools ā Contact Sync" to getcontacts_secret. Without it, only members within the app's visible scope can be read. - Message Reception (optional): Enable API reception in the app's "Receive Messages" settings to get
TokenandEncodingAESKey. For local development, use an intranet tunnel tool (e.g., ngrok, cloudflared) to expose the callback address.
Data Storage Structure
data/
āāā wecom_messages.db # SQLite database (yearly partitioned tables)
āāā files/
āāā 2026/
ā āāā 07/
ā ā āāā image_xxx.jpg
ā ā āāā report.pdf
ā āāā ...
āāā ...
š License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.