Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Server My Lark Doc search wiki for design specs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol server for searching and accessing Lark(Feishu) documents.
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
OAuth-based user authentication
Automatic token refresh and expiration management
Customizable OAuth callback server
Comprehensive error reporting for authentication issues
Clear feedback for invalid document URLs
Detailed error messages for troubleshooting
Related MCP server: feishu-mcp-server
uvx mcp-server-my-lark-docVisit the Lark Open Platform: https://open.larkoffice.com/app
wiki:wiki:readonly
wiki:node:read
docx:document:readonly
search:docs:readBefore 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 OAUTH_HOST="localhost" # OAuth callback server host (default: localhost)
export OAUTH_PORT="9997" # OAuth callback server port (default: 9997)Configure in Claude desktop:
"mcpServers": {
"lark_doc": {
"command": "uvx",
"args": ["mcp-server-my-lark-doc"],
"env": {
"LARK_APP_ID": "your app id",
"LARK_APP_SECRET": "your app secret",
"OAUTH_HOST": "localhost", // optional
"OAUTH_PORT": "9997" // optional
}
}
}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
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": ser didn't complete authorization within 5 minutes
Default configuration:
Host: localhost
Port: 9997 Customize via environment variables:
OAUTH_HOST: Set callback server host
OAUTH_PORT: Set callback server port
MIT License
Get Lark document content
Args:
documentUrl: Lark document URL
| Name | Required | Description | Default |
|---|---|---|---|
| documentUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description provides no behavioral information beyond the basic action. With no annotations, the description should disclose safety (e.g., read-only), authentication requirements, or error behavior, but it says nothing. This leaves the agent blind to important execution traits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short, but this is under-specification rather than conciseness. It lacks structure, such as separating the main description from parameter details. Every sentence does not earn its place because more essential information is omitted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, no annotations, and a single parameter, the description should explain the return value, expected behavior, and constraints (e.g., URL must be accessible). It provides nothing, making it wholly incomplete for an AI agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no description for the 'documentUrl' parameter, and the description only repeats the parameter name ('documentUrl: Lark document URL') without clarifying format, validity rules, or examples. Schema coverage is 0%, and the description fails to compensate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('Lark document content'), distinguishing it from the sibling 'search_wiki' which searches rather than retrieves content. However, it does not specify the format or scope of 'content' (e.g., plain text, structured data).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No usage guidance is provided. The description does not mention when to use this tool instead of 'search_wiki' or any other alternative. It simply states the function without context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Lark Wiki
Args:
query: Search keywords
page_size: Number of results to return (default: 10)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| page_size | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It fails to mention any side effects, rate limits, authentication needs, or result structure. The description is completely silent on behavioral aspects beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short (two lines for parameters) and follows a docstring format. While it is concise, it may be too sparse, omitting useful information that could fit without being verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should explain return values. It does not describe what the search results contain. Additionally, with a sibling tool available, no clarification of relationship is provided, leaving the agent with incomplete context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must add meaning. It describes 'query' as 'Search keywords' and 'page_size' as 'Number of results to return (default: 10).' This adds minimal semantics but does not explain expected format or behavior beyond defaults.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search Lark Wiki,' which clearly indicates a search verb and resource. However, it does not differentiate from the sibling tool get_lark_doc_content, which might retrieve content of a specific document. The purpose is clear but lacks distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use search_wiki versus the sibling tool get_lark_doc_content. The description does not mention alternatives or exclusions, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.6get_lark_doc_contentsearch_wikiThe two tools have clearly distinct purposes: one retrieves document content by URL, the other searches the wiki by keywords. There is no ambiguity or overlap.
Both tools use a consistent verb_noun pattern with snake_case: 'get_lark_doc_content' and 'search_wiki'. The naming convention is uniform and predictable.
With only 2 tools, the server feels underdeveloped for a document/wiki domain. Typical servers of this scope would include list, create, update, or delete operations, making this minimal.
The tool surface is incomplete for Lark Doc: it only provides content retrieval and wiki search, but lacks essential operations like listing documents, editing, or managing wiki pages. Major gaps exist.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Knowledge base MCP for AI agents on iknow.dev. Search, read, and maintain via OAuth.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Search your Glasp web and Kindle highlights, notes, and AI memories from any MCP client. Read-only.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/T0UGH/mcp_server_my_lark_doc'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
