lark-mcp-server
# Lark MCP Server / é£ä¹¦ MCP Server
> šØš³ The first Chinese MCP Server for Lark/Feishu ā let any AI client operate Feishu through MCP protocol.
> šØš³ é¦äøŖé£ä¹¦ MCP Server ā č®©ä»»ä½ AI 客ę·ē«Æéčæę å MCP åč®®ęä½é£ä¹¦ć
[](LICENSE)
[](pyproject.toml)
[](https://modelcontextprotocol.io)
## š Quick Start / åæ«éå¼å§
### Install / å®č£
```bash
# via pip
pip install lark-mcp-server
# or via uvx (no install needed)
uvx lark-mcp-server
```
### Prerequisites / åęę”ä»¶
You need [lark-cli](https://github.com/agent-garden/lark-cli) installed and authenticated:
```bash
# Install lark-cli & login
lark-cli auth login
```
### Configure with Claude Desktop / é
ē½®å° Claude Desktop
Add to your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"lark": {
"command": "uvx",
"args": ["lark-mcp-server"]
}
}
}
```
Now Claude can send/receive Feishu messages, list chats, and more! š¤
---
## š ļø Tools / å·„å
·å蔨
### š¬ IM Messages / ę¶ęÆ
| Tool | Description | 诓ę |
|------|-------------|------|
| `lark_send_message` | Send text/markdown to a chat | åéę¶ęÆå°č天 |
| `lark_reply_message` | Reply to a message | åå¤ę¶ęÆ |
| `lark_list_chats` | List group chats | ååŗē¾¤čå蔨 |
| `lark_get_chat_members` | Get chat member list | č·å群ęå |
| `lark_list_messages` | View chat history | ę„ēč天åå² |
| `lark_send_card` | Send interactive card | åéäŗ¤äŗå”ē |
### š¤ Contacts / č系人
| Tool | Description | 诓ę |
|------|-------------|------|
| `lark_get_user_info` | Get user information | č·åēØę·äæ”ęÆ |
### š
Calendar / ę„å
| Tool | Description | 诓ę |
|------|-------------|------|
| `lark_get_agenda` | View calendar agenda | ę„ēę„ēØå®ę |
---
## š” Use Cases / 使ēØåŗęÆ
### š¤ AI Agent Automates Feishu / Agent čŖåØå¤ēé£ä¹¦ę¶ęÆ
```python
# Your AI agent can now:
# - Monitor and reply to messages automatically
# - Send batch notifications to group chats
# - Check meeting schedules and notify attendees
```
### š Data Integration / ę°ę®éę
```python
# Connect Feishu with other tools via MCP:
# - Read Feishu messages ā process with AI ā write to database
# - Sync calendar events to your task manager
# - Automate HR onboarding workflows
```
### š Cross-platform Automation / č·Øå¹³å°čŖåØå
```python
# Feishu + GitHub + Slack = automated workflow
# All connected through standard MCP protocol
```
---
## š¦ Project Structure / 锹ē®ē»ę
```
lark-mcp-server/
āāā pyproject.toml # Python package config
āāā src/lark_mcp_server/
ā āāā server.py # MCP server entry, tool registration
ā āāā client.py # LarkClient ā lark-cli subprocess wrapper
āāā tests/
āāā test_client.py # Integration tests
```
---
## š Related Projects / ēøå
³é”¹ē®
- [lark-cli](https://github.com/agent-garden/lark-cli) ā Lark/Feishu CLI tool
- [YuanZhiTech](https://github.com/YuanZhiTech) ā Our Agent Garden organization
---
## š License
MIT Ā© 2026 Agent Garden
*Built by AI Agents, for AI Agents.* š¤
*ē± AI Agent ę建ļ¼äøŗ AI Agent ęå”ć*
TDQS
Scored across 8 tools
Each tool targets a distinct resource and action: sending, replying, listing chats, getting members, viewing messages, sending cards, user info, and agenda. While send_message and send_card both send to a chat, their descriptions clearly distinguish text from interactive cards, leaving no ambiguity.
All tool names follow the same pattern: lark_verb_noun (e.g., lark_send_message, lark_list_chats). The verbs are consistent (send, reply, list, get) and all use snake_case, making the naming uniform and predictable.
With 8 tools, the server is well-scoped for a collaboration platform covering messaging, chat management, user info, and agenda reading. Each tool earns its place without being overwhelming or sparse.
The server covers core messaging workflows (send, reply, list history) and read operations for chats and users, but lacks write operations for chats (create/update/delete), message editing/deletion, and calendar management beyond reading. These gaps could cause agents to hit dead ends when trying to manage resources.