Welink
🔍微信聊天数据分析的本地化AI-agent(Docker/Windows/MacOS) · AI分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像
What is Welink?
Welink is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🔍微信聊天数据分析的本地化ai-agent(docker/windows/macos) · ai分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像
🔍微信聊天数据分析的本地化AI-agent(Docker/Windows/MacOS) · AI分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像
This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🔍微信聊天数据分析的本地化AI-agent(Docker/Windows/MacOS) · AI分身 / 大模型分析 /
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx welinkConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Welink
WeLink is a local AI-powered analysis platform for WeChat (Weixin) chat data. It decrypts and indexes your WeChat message history, then exposes it through an MCP server so that AI assistants like Claude can query conversations, generate relationship timelines, detect sentiment trends, produce word clouds, and simulate group chat dynamics — all processed entirely on your local machine. It runs on macOS, Windows, and via Docker, and supports over 25 LLM providers including OpenAI, DeepSeek, Gemini, and local Ollama models.
Prerequisites
- macOS 12+, Windows 10 1903+, or Docker installed for the containerized deployment
- WeChat installed with an existing message database (WeLink only reads your local chat history)
- The wechat-decrypt tool (https://github.com/ylytdeng/wechat-decrypt) to export a decrypted copy of your WeChat database
- API key for at least one supported LLM provider (OpenAI, DeepSeek, Claude, Gemini, or a local Ollama endpoint)
- An MCP-compatible client such as Claude Code CLI to use the MCP server feature
Decrypt your WeChat database
Use the wechat-decrypt tool to export your WeChat message history to a decrypted/ directory. WeLink reads this directory at startup and will not have access to live WeChat traffic.
git clone https://github.com/ylytdeng/wechat-decrypt.git
cd wechat-decrypt && python3 decrypt.pyInstall and launch WeLink
On macOS, download WeLink.dmg from the GitHub releases page and drag it to /Applications. On Windows, extract WeLink-windows-amd64.zip and run WeLink.exe. For Docker, use the provided compose file.
# Docker deployment
git clone https://github.com/runzhliu/welink.git
cd welink && docker compose upPoint WeLink to the decrypted data directory
In the WeLink settings UI, set the data source path to the decrypted/ directory produced by wechat-decrypt. WeLink will index your messages (indexing time scales with data size: under 30 seconds for <500K messages).
Configure your LLM provider
In WeLink Settings, choose your LLM provider and enter your API key. The default is DeepSeek; you can switch to OpenAI, Claude, Gemini, or any of the 25+ supported providers.
Enable the MCP server
In WeLink Settings, enable the built-in MCP server. It exposes WeChat query tools on a local endpoint. Add it to your Claude Code or other MCP client config to use natural-language queries over your chat history.
{
"mcpServers": {
"welink": {
"command": "npx",
"args": ["welink"],
"env": {}
}
}
}Welink Examples
Client configuration
Example claude_desktop_config.json entry to connect to a locally running WeLink MCP server. The WeLink app must be running before the MCP client starts.
{
"mcpServers": {
"welink": {
"type": "sse",
"url": "http://localhost:8080/sse"
}
}
}Prompts to try
Natural-language prompts for querying your WeChat history through an AI assistant.
- "Who do I chat with the most? Rank my top 10 contacts by message count"
- "Show the sentiment trend in my conversations with Alice over the past 6 months"
- "Generate a word cloud for my group chat '家庭群'"
- "Summarize all messages from Bob this year and identify recurring topics"
- "Which relationships have gone cold? Show contacts I used to message frequently but haven't in 3 months"
- "Search for all messages where someone mentioned 'project deadline' this quarter"Troubleshooting Welink
WeLink blocked by macOS Gatekeeper on first launch
Right-click the WeLink.app icon and choose Open, then confirm in the dialog. Alternatively, run `xattr -cr /Applications/WeLink.app` in Terminal to remove the quarantine attribute.
Indexing is very slow or runs out of memory
For large databases (2M+ messages), WeLink requires 8GB+ of RAM. Close other applications during indexing. Consider running the Docker deployment on a machine with adequate resources, or split large databases.
LLM responses are slow or time out
Check your API key and provider connectivity in WeLink Settings → Diagnostics. For faster local processing, switch to Ollama with a small model (e.g., llama3.1:8b). Ensure the Ollama server is running at its default port.
Frequently Asked Questions about Welink
What is Welink?
Welink is a Model Context Protocol (MCP) server that 🔍微信聊天数据分析的本地化ai-agent(docker/windows/macos) · ai分身 / 大模型分析 / 好友排行 / 词云 / 情感趋势 / 群聊画像 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Welink?
Follow the installation instructions on the Welink GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Welink?
Welink works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Welink free to use?
Yes, Welink is open source and available under the AGPL-3.0 license. You can use it freely in both personal and commercial projects.
Welink Alternatives — Similar Communication Servers
Looking for alternatives to Welink? Here are other popular communication servers you can use with Claude, Cursor, and VS Code.
Slack
★ 86.1kEnables interaction with Slack workspaces through comprehensive channel management, messaging, user management, file uploads, and Block Kit formatting. Features secure credential storage via macOS Keychain and supports all major Slack operations incl
LibreChat
★ 37.3kEnhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenA
Note Gen
★ 11.9kA cross-platform Markdown AI note-taking software.
DeepChat
★ 5.8k🐬DeepChat - A smart assistant that connects powerful AI to your personal world
WhatsApp MCP
★ 5.7kConnects AI assistants to the official Meta WhatsApp Cloud API for managing conversations and sending various message types through natural language. It provides tools for media management, template messages, and real-time webhook processing without
Apple
★ 3.1kEnables interaction with Apple apps like Messages, Notes, and Contacts through the MCP protocol to send messages, search, and open app content using natural language.
Browse More Communication MCP Servers
Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Welink in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Welink?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.