I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

mcp_lark_doc_manage
base on origin lark mcp-server modified, add dictionary support
3 years
Works with Finder
0
Github Watches
0
Github Forks
0
Github Stars
MCP Lark Doc Manage
A Model Context Protocol server for searching and accessing Lark(Feishu) documents.
Important: Before using this MCP Server, you need to have a Lark Enterprise Application. If you haven't created one yet, please follow the setup instructions below.
Features
Document Content Access
- Supports both Lark Doc and Wiki document types
- Automatically handles document type detection and ID extraction
- Returns raw content in text format for LLM processing
Authentication
- OAuth-based user authentication
- Automatic token refresh and expiration management
- Customizable OAuth callback server
Error Handling
- Comprehensive error reporting for authentication issues
- Clear feedback for invalid document URLs
- Detailed error messages for troubleshooting
Installation
uvx mcp-lark-doc-manage
Configuration
Create Your Lark Enterprise Application
- Visit Lark Open Platform
- Click "Developer Console" in the top right corner
- Click "Create Custom App"
- Fill in the basic information:
- App Name
- App Description
- App Icon
- In the "Security Settings" section:
- Add your domain to "Request Domain Name Whitelist"
- Configure OAuth 2.0 settings
- Enable required capabilities and apply for permissions in "Permission Management"
- Submit for review and wait for approval
For detailed instructions, see Custom App Development Process.
Get App ID and App Secret
-
Get App ID:
- Go to your app in Developer Console
- Find "App ID" (also called "Client ID") in "Credentials & Basic Info"
- It usually starts with "cli_" for internal apps
-
Get App Secret:
- In the same "Credentials & Basic Info" page
- Find "App Secret" (also called "Client Secret")
- Click "View" to see the secret
- Note: Keep your App Secret secure and never share it publicly
Get Folder Token
To get a folder token:
- Open the target folder in Lark
- Copy the folder URL, for example:
https://xxx.feishu.cn/drive/folder/xxx
- The last segment in the URL is your folder token
- Alternative method:
- Use the Drive API to list folders
- Find the target folder's token in the response
Note: Make sure your app has the drive:drive:readonly
permission to access folders.
Required Permissions
wiki:node:read # Wiki node read access
docx:document:readonly # Document read-only access
search:docs:read # Document search access
drive:drive:readonly # Drive read-only access
Environment Variables
Before using this MCP server, you need to set up your Lark application credentials:
- Create a Lark application in Lark Open Platform
- Get your App ID and App Secret
- Configure environment variables:
export LARK_APP_ID="your_app_id"
export LARK_APP_SECRET="your_app_secret"
export FOLDER_TOKEN="your_folder_token" # Specified folder token
export OAUTH_HOST="localhost" # OAuth callback server host (default: localhost)
export OAUTH_PORT="9997" # OAuth callback server port (default: 9997)
Usage
Configure in Claude desktop:
"mcpServers": {
"lark_doc": {
"command": "/path/to/your/uvx",
"args": [
"mcp-lark-doc-manage"
],
"env": {
"LARK_APP_ID": "your_app_id",
"LARK_APP_SECRET": "your_app_secret",
"OAUTH_HOST": "localhost",
"OAUTH_PORT": "9997",
"FOLDER_TOKEN": "your_folder_token",
"DEBUG": "1" // optional, enable debug mode
}
}
}
Note: Replace /path/to/your/uvx
with your actual uvx path (e.g., /Users/username/anaconda3/bin/uvx
).
Available Tools
-
get_lark_doc_content
- Purpose: Retrieve document content from Lark
- Args: documentUrl (string) - The URL of the Lark document
- Returns: Document content in text format
- Supports:
- Doc URLs: https://xxx.feishu.cn/docx/xxxxx
- Wiki URLs: https://xxx.feishu.cn/wiki/xxxxx
-
search_wiki
- Purpose: Search documents in Lark Wiki
- Args:
- query (string) - Search keywords
- page_size (int, optional) - Number of results to return (default: 10)
- Returns: JSON string containing search results with following fields:
- title: Document title
- url: Document URL
- create_time: Document creation time
- update_time: Document last update time
-
list_folder_content
- Purpose: List contents of a specified folder
- Args:
- page_size (int, optional) - Number of results to return (default: 10)
- Returns: JSON string containing file list with following fields:
- name: File name
- type: File type
- token: File token
- url: File URL
- create_time: Creation time
- edit_time: Last edit time
- owner_id: Owner ID
-
create_doc
- Purpose: Create a new Lark document with content
- Args:
- title (string) - Document title
- content (string, optional) - Document content in Markdown format
- target_space_id (string, optional) - Target wiki space ID to move the document to
- Returns: JSON string containing:
- document_id: Created document ID
- title: Document title
- url: Document URL
- Features:
- Supports Markdown content conversion
- Optional wiki space integration
- Automatic folder placement
Error Messages
Common error messages and their solutions:
- "Lark client not properly initialized": Check your LARK_APP_ID and LARK_APP_SECRET
- "Invalid Lark document URL format": Verify the document URL format
- "Failed to get document content": Check document permissions and token validity
- "Failed to get app access token": Check your application credentials and network connection
- "Failed to get wiki document real ID": Check if the wiki document exists and you have proper permissions
- "Document content is empty": The document might be empty or you might not have access to its content
- "Authorization timeout": User didn't complete authorization within 5 minutes
- "Folder token not configured": Check your FOLDER_TOKEN environment variable
Development Notes
OAuth Callback Server
Default configuration:
- Host: localhost
- Port: 9997
Customize via environment variables:
- OAUTH_HOST: Set callback server host
- OAUTH_PORT: Set callback server port
License
MIT License
相关推荐
Converts Figma frames into front-end code for various mobile frameworks.
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.
Advanced software engineer GPT that excels through nailing the basics.
Delivers concise Python code and interprets non-English comments
A unified API gateway for integrating multiple etherscan-like blockchain explorer APIs with Model Context Protocol (MCP) support for AI assistants.
Mirror ofhttps://github.com/suhail-ak-s/mcp-typesense-server
本项目是一个钉钉MCP(Message Connector Protocol)服务,提供了与钉钉企业应用交互的API接口。项目基于Go语言开发,支持员工信息查询和消息发送等功能。
Short and sweet example MCP server / client implementation for Tools, Resources and Prompts.
Reviews

user_4yzR8b8p
mcp_lark_doc_manage by Xeonice is an outstanding document management tool! It offers seamless integration, is user-friendly, and significantly enhances productivity. The features are robust, making document handling a breeze. Highly recommend for anyone looking to streamline their workflow! More details at https://github.com/Xeonice/mcp_lark_doc_manage.