Lark Doc
An MCP server for searching and accessing Lark documents, supporting functions such as document content retrieval, OAuth authentication, and error handling.
2 points
9.8K

What is MCP Lark Doc Manage?

MCP Lark Doc Manage is a middleware service that connects Lark documents with AI models, allowing AI assistants to securely access and operate on the content of your Lark documents. It provides functions such as document content reading, search, and creation.

How to use MCP Lark Doc Manage?

Before use, you need to configure the authorization of the Lark enterprise application, and then you can access the document content through simple API calls. The system will automatically handle authentication and document type recognition.

Applicable scenarios

Suitable for scenarios where an AI assistant is needed to help organize, summarize, or analyze the content of Lark documents, such as automatically generating meeting minutes and answering questions about document content.

Main features

Document content access
Supports two document types, Lark documents and Wikis. Automatically identifies the document type and extracts the content, returning it in plain text format for easy AI processing.
Security authentication
User authentication based on OAuth, automatically manages token refresh and expiration to ensure data security.
Document search
Supports searching for Wiki documents by keywords and can return results sorted by relevance.
Document creation
Supports creating new documents and adding content, with the option to input in Markdown format.
Advantages
Seamless integration with the Lark document system
Automatically handles complex authentication processes
Supports multiple document types and operations
Returns content in a format suitable for AI processing
Limitations
Requires authorization from the enterprise administrator for the application
Document access is restricted by the Lark permission system
Technical knowledge is required for the initial configuration

How to use

Create a Lark enterprise application
Create an enterprise application on the Lark Open Platform and obtain the App ID and App Secret.
Configure environment variables
Set necessary environment variables such as LARK_APP_ID and LARK_APP_SECRET.
Install and start the service
Use the uvx tool to install and start the MCP service.
Configure the Claude desktop client
Add the MCP server information to the Claude configuration.

Usage examples

Get the content of meeting minutes
Let the AI assistant read and summarize the meeting minutes document
Search for project documents
Search for relevant project documents in the Wiki
Create a weekly report document
Let the AI assistant automatically create a weekly report document

Frequently Asked Questions

Why can't I access some documents?
How to obtain the folder_token?
What should I do if the document content returned is empty?
What should I do if the OAuth authorization fails?

Related resources

Lark Open Platform
Lark developer documentation and API reference
Custom application development process
How to create a custom Lark application
GitHub repository
Project source code and issue tracking

Installation

Copy the following command to your Client for configuration
"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: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
6.6K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.3K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
4.9K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
4.3K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
5.5K
4 points
P
Paperbanana
Python
7.8K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
6.5K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
7.7K
5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.8K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.0K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.6K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
74.1K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.3K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.7K
5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.1K
4.7 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.1K
4.5 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase