What can @larksuiteoapi/lark-mcp do?

feishu/lark api resource exposure via mcp protocol, lark openapi schema-to-mcp tool translation, multi-tenant lark api credential management, lark document and knowledge base access via mcp, lark messaging and notification dispatch via mcp, lark calendar and event management via mcp, lark user and organization data access via mcp, mcp protocol compliance and client compatibility

@larksuiteoapi/lark-mcp

MCP ServerFree

Feishu/Lark OpenAPI MCP

Open Source

/ 100

8 capabilities

Capabilities8 decomposed

feishu/lark api resource exposure via mcp protocol

Medium confidence

Exposes Feishu/Lark OpenAPI endpoints as MCP tools through a standardized Model Context Protocol interface, enabling LLM clients (Claude, etc.) to invoke Lark API operations without direct HTTP knowledge. Implements MCP server pattern with tool schema generation from Lark's OpenAPI specification, translating REST endpoints into callable functions with parameter validation and response marshaling.

Solves for

I want Claude or another LLM to read/write data in my Lark workspace without me writing custom integration codeI need to automate Lark operations (create documents, send messages, manage calendars) through natural language promptsI'm building an AI agent that needs to interact with Lark as a data source and action sink

Best for

Teams using Feishu/Lark as their primary workspace platform who want AI-driven automation

Developers building LLM agents that need to interact with Lark's ecosystem

Organizations migrating from REST API calls to MCP-based LLM integrations

Requires

Node.js 14+ (npm package)

Lark/Feishu tenant with OpenAPI access enabled

Valid Lark API credentials (app_id, app_secret, or user token)

Limitations

Requires valid Lark API credentials (tenant access token or user token) — no anonymous access

MCP protocol overhead adds ~50-200ms per request compared to direct REST calls

Limited to Lark OpenAPI surface — custom Lark extensions or webhooks not exposed

What makes it unique

Implements MCP server pattern specifically for Lark's OpenAPI, translating Lark's REST API surface into MCP tool schemas with automatic parameter validation and response marshaling — bridges proprietary Lark ecosystem with standardized LLM tool-calling protocol

vs alternatives

Provides native MCP integration for Lark whereas direct REST API calls require custom LLM prompt engineering and lack standardized tool schema validation

lark openapi schema-to-mcp tool translation

Medium confidence

Automatically converts Lark OpenAPI specifications into MCP-compliant tool definitions with JSON schema validation, parameter descriptions, and response type mapping. Parses Lark's OpenAPI documentation and generates executable tool handlers that validate inputs against schema constraints before forwarding to Lark API endpoints.

Solves for

I want to expose Lark API endpoints as callable tools without manually writing tool definitionsI need parameter validation and type checking before sending requests to LarkI want my LLM to understand what parameters each Lark API operation accepts

Best for

Developers automating Lark API exposure to LLMs

Teams building internal tools that bridge Lark and AI systems

Organizations standardizing on MCP for LLM integrations

Requires

Node.js 14+

Knowledge of MCP tool schema format

Lark API credentials to test translated tools

Limitations

Schema translation is one-way — changes to Lark OpenAPI require package updates

Complex nested object schemas may not translate perfectly to MCP tool schemas

Enum values and conditional parameters may lose semantic context in translation

What makes it unique

Implements automatic OpenAPI-to-MCP schema translation with built-in parameter validation, ensuring LLM tool calls conform to Lark API constraints before execution — reduces manual tool definition work

vs alternatives

Eliminates manual tool schema writing for Lark APIs compared to hand-coded MCP servers or generic REST-to-MCP adapters

multi-tenant lark api credential management

Medium confidence

Manages authentication tokens for multiple Lark tenants/workspaces, supporting both app-level credentials (app_id/app_secret) and user-level tokens. Handles token lifecycle including refresh, expiration tracking, and credential isolation per tenant, enabling a single MCP server instance to serve multiple Lark workspaces simultaneously.

Solves for

I need to connect multiple Lark workspaces to a single AI agentI want to manage API credentials securely without hardcoding themI need to switch between different Lark tenants in a single session

Best for

Multi-tenant SaaS platforms integrating Lark

Enterprises with multiple Lark workspaces

Developers building Lark integrations for multiple customers

Requires

Node.js 14+

Valid Lark app credentials (app_id, app_secret) or user tokens

Environment variable configuration or startup parameter passing

Limitations

Token refresh logic depends on Lark's token expiration windows — no custom TTL override

Credentials must be provided at server startup or via environment variables — no runtime credential injection

No built-in credential encryption — relies on environment variable security

What makes it unique

Implements multi-tenant credential isolation within a single MCP server instance, managing token lifecycle and refresh for multiple Lark workspaces — enables shared infrastructure for multi-customer deployments

vs alternatives

Supports multi-tenant scenarios natively whereas single-tenant MCP servers require separate instances per workspace

lark document and knowledge base access via mcp

Medium confidence

Exposes Lark's document management and knowledge base APIs through MCP tools, enabling LLMs to read, search, and retrieve content from Lark Docs, Sheets, and Wikis. Implements document retrieval with pagination support and full-text search capabilities, translating Lark's document hierarchy into queryable resources for AI agents.

Solves for

I want Claude to search and read documents stored in my Lark workspaceI need an AI agent to retrieve specific information from Lark Docs or WikisI want to build a knowledge base chatbot that pulls from Lark documents

Best for

Teams using Lark as a knowledge management system

Organizations building AI-powered document search

Developers creating knowledge base chatbots backed by Lark

Requires

Node.js 14+

Lark API credentials with document access permissions

Lark workspace with documents/wikis to retrieve

Limitations

Document retrieval is read-only — no document creation/editing through MCP

Large documents may exceed LLM context windows — requires chunking or summarization

Search is limited to Lark's built-in search capabilities — no custom indexing

What makes it unique

Integrates Lark's document APIs with MCP tool schema, enabling LLMs to query and retrieve Lark documents with full pagination and search support — treats Lark as a queryable knowledge source

vs alternatives

Provides native Lark document access compared to generic document retrieval systems that require manual Lark integration

lark messaging and notification dispatch via mcp

Medium confidence

Exposes Lark's messaging APIs through MCP tools, enabling LLMs to send messages, create threads, and post notifications to Lark chats, groups, and individual users. Implements message formatting with support for rich text, mentions, and interactive elements, translating LLM outputs into Lark message payloads.

Solves for

I want an AI agent to send notifications to Lark when certain conditions occurI need Claude to post messages to specific Lark chat groups based on user requestsI want to build a Lark bot that responds to queries with formatted messages

Best for

Teams automating Lark notifications from AI systems

Developers building Lark chatbots powered by LLMs

Organizations creating AI-driven workflow notifications

Requires

Node.js 14+

Lark API credentials with messaging permissions

Valid Lark chat IDs or user IDs for message recipients

Limitations

Message formatting is limited to Lark's supported rich text — no arbitrary HTML/Markdown

Cannot edit or delete messages after sending — only create new messages

Rate limiting applies per Lark API — high-volume messaging may be throttled

What makes it unique

Wraps Lark's messaging APIs as MCP tools with support for rich message formatting and multi-recipient dispatch — enables LLMs to generate and send structured Lark messages

vs alternatives

Provides native Lark messaging integration compared to generic notification systems that require custom Lark API wrappers

lark calendar and event management via mcp

Medium confidence

Exposes Lark's calendar and event APIs through MCP tools, enabling LLMs to create events, query calendars, and manage meeting schedules. Implements event creation with attendee management, time zone handling, and conflict detection, translating natural language scheduling requests into Lark calendar operations.

Solves for

I want an AI agent to schedule meetings in Lark based on natural language requestsI need Claude to check calendar availability and suggest meeting timesI want to automate event creation in Lark when certain conditions are met

Best for

Teams automating meeting scheduling through AI

Organizations building AI-powered calendar assistants

Developers creating Lark-integrated scheduling bots

Requires

Node.js 14+

Lark API credentials with calendar permissions

Valid Lark user IDs for event attendees

Limitations

Calendar queries are limited to the authenticated user's calendar — no cross-user calendar access

Event creation requires explicit attendee IDs — no fuzzy name matching

Time zone handling depends on Lark's configured time zones — no custom zone support

What makes it unique

Integrates Lark's calendar APIs with MCP tool schema, enabling LLMs to parse natural language scheduling requests and execute calendar operations with attendee management — bridges conversational scheduling with Lark's event system

vs alternatives

Provides native Lark calendar integration compared to generic scheduling tools that require separate Lark API integration

lark user and organization data access via mcp

Medium confidence

Exposes Lark's user management and organization APIs through MCP tools, enabling LLMs to query user profiles, department structures, and organizational hierarchies. Implements user search with filtering and pagination, translating organizational queries into Lark API calls for context-aware operations.

Solves for

I want an AI agent to look up user information from my Lark organizationI need Claude to understand the organizational structure for routing decisionsI want to automate user-related operations based on organizational context

Best for

Large organizations using Lark with complex hierarchies

Teams building AI-powered HR or admin automation

Developers creating context-aware Lark bots

Requires

Node.js 14+

Lark API credentials with user/organization read permissions

Appropriate Lark admin or user role for data access

Limitations

User data access is limited by authenticated user's permissions — cannot query all users if not admin

User search is limited to Lark's built-in search fields — no custom attribute search

Organizational hierarchy is read-only — no user creation/modification through MCP

What makes it unique

Exposes Lark's user and organization APIs as MCP tools with search and filtering capabilities — enables LLMs to understand organizational context for routing and personalization

vs alternatives

Provides native Lark organizational data access compared to generic directory systems that require separate Lark integration

mcp protocol compliance and client compatibility

Medium confidence

Implements full Model Context Protocol (MCP) server specification, ensuring compatibility with MCP-compliant clients (Claude Desktop, custom MCP clients, etc.). Handles MCP request/response marshaling, tool invocation routing, and error handling according to MCP standards, enabling seamless integration with any MCP-compatible LLM platform.

Solves for

I want to use this Lark integration with Claude Desktop or other MCP clientsI need to ensure my Lark MCP server works with multiple LLM platformsI want to build custom MCP clients that can invoke Lark operations

Best for

Developers integrating Lark with MCP-compatible LLM platforms

Organizations standardizing on MCP for AI integrations

Teams building custom MCP clients

Requires

Node.js 14+

MCP-compatible client (Claude Desktop, custom implementation, etc.)

Understanding of MCP protocol and tool schema format

Limitations

MCP protocol overhead adds latency compared to direct API calls

Client support for MCP is still emerging — not all LLM platforms have native MCP

Tool schema complexity may exceed some client's parsing capabilities

What makes it unique

Implements full MCP server specification with proper request/response marshaling and error handling — ensures compatibility with any MCP-compliant client without custom adapters

vs alternatives

Provides standards-compliant MCP implementation compared to proprietary integration approaches that lock into specific LLM platforms

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Related Artifactssharing capabilities

Artifacts that share capabilities with @larksuiteoapi/lark-mcp, ranked by overlap. Discovered automatically through the match graph.

MCP Server26

@mseep/airylark-mcp-server

AiryLark的ModelContextProtocol(MCP)服务器，提供高精度翻译API

mcp-compliant translation service exposureopenai api integration for translation backend

2 shared capabilities

MCP Server30

@ivotoby/openapi-mcp-server

An MCP server that exposes OpenAPI endpoints as resources

openapi schema introspection and resource exposureauthentication and credential management for rest apis

2 shared capabilities

MCP Server44

Cloudflare MCP Server

Manage Cloudflare Workers, KV, R2, and DNS via MCP.

dual-mode authentication with oauth 2.0 and api token supportmcp-compliant tool exposure via http streaming transport

2 shared capabilities

MCP Server28

4everland/4everland-hosting-mcp

** - An MCP server implementation for 4EVERLAND Hosting enabling instant deployment of AI-generated code to decentralized storage networks like Greenfield, IPFS, and Arweave.

authentication and credential management for multi-network deploymentsmcp tool schema generation and registration for 4everland hosting apis

2 shared capabilities

MCP Server32

@ivotoby/openapi-mcp-server

An MCP server that exposes OpenAPI endpoints as resources

openapi schema introspection and resource exposure

1 shared capability

MCP Server23

@iflow-mcp/figma-mcp

ModelContextProtocol server for Figma

figma authentication and credential management

1 shared capability

Best For

✓Teams using Feishu/Lark as their primary workspace platform who want AI-driven automation
✓Developers building LLM agents that need to interact with Lark's ecosystem
✓Organizations migrating from REST API calls to MCP-based LLM integrations
✓Developers automating Lark API exposure to LLMs
✓Teams building internal tools that bridge Lark and AI systems
✓Organizations standardizing on MCP for LLM integrations
✓Multi-tenant SaaS platforms integrating Lark
✓Enterprises with multiple Lark workspaces

Known Limitations

⚠Requires valid Lark API credentials (tenant access token or user token) — no anonymous access
⚠MCP protocol overhead adds ~50-200ms per request compared to direct REST calls
⚠Limited to Lark OpenAPI surface — custom Lark extensions or webhooks not exposed
⚠No built-in caching or request batching — each LLM tool invocation triggers a separate API call
⚠Depends on MCP client support — not all LLM platforms have native MCP integration
⚠Schema translation is one-way — changes to Lark OpenAPI require package updates

Requirements

Node.js 14+ (npm package)Lark/Feishu tenant with OpenAPI access enabledValid Lark API credentials (app_id, app_secret, or user token)MCP-compatible client (Claude Desktop, custom MCP client, etc.)Node.js 14+Knowledge of MCP tool schema formatLark API credentials to test translated toolsValid Lark app credentials (app_id, app_secret) or user tokens

Input / Output

Accepts: JSON parameters matching Lark OpenAPI schemas, Natural language prompts (processed by LLM client into tool calls), Structured tool invocation requests from MCP client, Lark OpenAPI specification (bundled), Tool invocation parameters as JSON, Lark app_id and app_secret, Lark user access tokens, Tenant identifier for multi-tenant requests, Document IDs or search queries, Pagination parameters, Filter criteria (document type, owner, etc.), Message content as text or structured format, Recipient identifiers (chat_id, user_id, group_id), Message formatting options (mentions, links, etc.), Event details (title, description, start/end time), Attendee list (user IDs or email addresses), Calendar query parameters (date range, filters), User search queries (name, email, ID), Department/organization filters, MCP protocol requests (JSON-RPC format), Tool invocation requests with parameters

Produces: JSON responses from Lark API, Structured tool results conforming to MCP response schema, Error messages with Lark API error codes, MCP tool schema definitions (JSON), Validated parameter objects, Tool execution results, Authenticated API requests to Lark, Token refresh confirmations, Credential validation status, Document content as text or structured data, Document metadata (title, owner, creation date), Search result lists with relevance scores, Message send confirmation with message_id, Error responses if recipient not found or permission denied, Message metadata (timestamp, sender), Event creation confirmation with event_id, Calendar availability data, Event metadata (attendees, time, location), User profile data (name, email, department, role), Organization hierarchy structure, User search results with metadata, MCP protocol responses (JSON-RPC format), Error responses conforming to MCP spec

UnfragileRank

Adoption50%(25% weight)

Quality17%(25% weight)

Ecosystem45%(15% weight)

Match Graph25%(30% weight)

Freshness75%(5% weight)

UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.

Type: MCP Server

8 capabilities

Visit @larksuiteoapi/lark-mcp→

Package Details

npm

Registry

0.5.1

Version

16,531

Weekly Downloads

About

Feishu/Lark OpenAPI MCP

Alternatives to @larksuiteoapi/lark-mcp

IntelliCode46Extension

AI-assisted development

Compare →

GitHub Copilot Chat49Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot48Extension

Your AI pair programmer

Compare →

Claude Code for VS Code48Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

Are you the builder of @larksuiteoapi/lark-mcp?

Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.

Claim this artifact →Verification via email

Get the weekly brief

New tools, rising stars, and what's actually worth your time. No spam.

Data Sources

mcp registry

Looking for something else?

Search →

Capabilities8 decomposed

feishu/lark api resource exposure via mcp protocol

Medium confidence

Solves for

Best for

Teams using Feishu/Lark as their primary workspace platform who want AI-driven automation

Developers building LLM agents that need to interact with Lark's ecosystem

Organizations migrating from REST API calls to MCP-based LLM integrations

Requires

Node.js 14+ (npm package)

Lark/Feishu tenant with OpenAPI access enabled

Valid Lark API credentials (app_id, app_secret, or user token)

Limitations

Requires valid Lark API credentials (tenant access token or user token) — no anonymous access

MCP protocol overhead adds ~50-200ms per request compared to direct REST calls

Limited to Lark OpenAPI surface — custom Lark extensions or webhooks not exposed

What makes it unique

vs alternatives

Provides native MCP integration for Lark whereas direct REST API calls require custom LLM prompt engineering and lack standardized tool schema validation

lark openapi schema-to-mcp tool translation

Medium confidence

Solves for

Best for

Developers automating Lark API exposure to LLMs

Teams building internal tools that bridge Lark and AI systems

Organizations standardizing on MCP for LLM integrations

Requires

Node.js 14+

Knowledge of MCP tool schema format

Lark API credentials to test translated tools

Limitations

Schema translation is one-way — changes to Lark OpenAPI require package updates

Complex nested object schemas may not translate perfectly to MCP tool schemas

Enum values and conditional parameters may lose semantic context in translation

What makes it unique

vs alternatives

Eliminates manual tool schema writing for Lark APIs compared to hand-coded MCP servers or generic REST-to-MCP adapters

multi-tenant lark api credential management

Medium confidence

Solves for

I need to connect multiple Lark workspaces to a single AI agentI want to manage API credentials securely without hardcoding themI need to switch between different Lark tenants in a single session

Best for

Multi-tenant SaaS platforms integrating Lark

Enterprises with multiple Lark workspaces

Developers building Lark integrations for multiple customers

Requires

Node.js 14+

Valid Lark app credentials (app_id, app_secret) or user tokens

Environment variable configuration or startup parameter passing

Limitations

Token refresh logic depends on Lark's token expiration windows — no custom TTL override

Credentials must be provided at server startup or via environment variables — no runtime credential injection

No built-in credential encryption — relies on environment variable security

What makes it unique

vs alternatives

Supports multi-tenant scenarios natively whereas single-tenant MCP servers require separate instances per workspace

lark document and knowledge base access via mcp

Medium confidence

Solves for

Best for

Teams using Lark as a knowledge management system

Organizations building AI-powered document search

Developers creating knowledge base chatbots backed by Lark

Requires

Node.js 14+

Lark API credentials with document access permissions

Lark workspace with documents/wikis to retrieve

Limitations

Document retrieval is read-only — no document creation/editing through MCP

Large documents may exceed LLM context windows — requires chunking or summarization

Search is limited to Lark's built-in search capabilities — no custom indexing

What makes it unique

Integrates Lark's document APIs with MCP tool schema, enabling LLMs to query and retrieve Lark documents with full pagination and search support — treats Lark as a queryable knowledge source

vs alternatives

Provides native Lark document access compared to generic document retrieval systems that require manual Lark integration

lark messaging and notification dispatch via mcp

Medium confidence

Solves for

Best for

Teams automating Lark notifications from AI systems

Developers building Lark chatbots powered by LLMs

Organizations creating AI-driven workflow notifications

Requires

Node.js 14+

Lark API credentials with messaging permissions

Valid Lark chat IDs or user IDs for message recipients

Limitations

Message formatting is limited to Lark's supported rich text — no arbitrary HTML/Markdown

Cannot edit or delete messages after sending — only create new messages

Rate limiting applies per Lark API — high-volume messaging may be throttled

What makes it unique

Wraps Lark's messaging APIs as MCP tools with support for rich message formatting and multi-recipient dispatch — enables LLMs to generate and send structured Lark messages

vs alternatives

Provides native Lark messaging integration compared to generic notification systems that require custom Lark API wrappers

lark calendar and event management via mcp

Medium confidence

Solves for

Best for

Teams automating meeting scheduling through AI

Organizations building AI-powered calendar assistants

Developers creating Lark-integrated scheduling bots

Requires

Node.js 14+

Lark API credentials with calendar permissions

Valid Lark user IDs for event attendees

Limitations

Calendar queries are limited to the authenticated user's calendar — no cross-user calendar access

Event creation requires explicit attendee IDs — no fuzzy name matching

Time zone handling depends on Lark's configured time zones — no custom zone support

What makes it unique

vs alternatives

Provides native Lark calendar integration compared to generic scheduling tools that require separate Lark API integration

lark user and organization data access via mcp

Medium confidence

Solves for

Best for

Large organizations using Lark with complex hierarchies

Teams building AI-powered HR or admin automation

Developers creating context-aware Lark bots

Requires

Node.js 14+

Lark API credentials with user/organization read permissions

Appropriate Lark admin or user role for data access

Limitations

User data access is limited by authenticated user's permissions — cannot query all users if not admin

User search is limited to Lark's built-in search fields — no custom attribute search

Organizational hierarchy is read-only — no user creation/modification through MCP

What makes it unique

Exposes Lark's user and organization APIs as MCP tools with search and filtering capabilities — enables LLMs to understand organizational context for routing and personalization

vs alternatives

Provides native Lark organizational data access compared to generic directory systems that require separate Lark integration

mcp protocol compliance and client compatibility

Medium confidence

Solves for

Best for

Developers integrating Lark with MCP-compatible LLM platforms

Organizations standardizing on MCP for AI integrations

Teams building custom MCP clients

Requires

Node.js 14+

MCP-compatible client (Claude Desktop, custom implementation, etc.)

Understanding of MCP protocol and tool schema format

Limitations

MCP protocol overhead adds latency compared to direct API calls

Client support for MCP is still emerging — not all LLM platforms have native MCP

Tool schema complexity may exceed some client's parsing capabilities

What makes it unique

Implements full MCP server specification with proper request/response marshaling and error handling — ensures compatibility with any MCP-compliant client without custom adapters

vs alternatives

Provides standards-compliant MCP implementation compared to proprietary integration approaches that lock into specific LLM platforms

Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.

Alternatives to @larksuiteoapi/lark-mcp

IntelliCode46Extension

AI-assisted development

Compare →

GitHub Copilot Chat49Extension

AI chat features powered by Copilot

Compare →

GitHub Copilot48Extension

Your AI pair programmer

Compare →

Claude Code for VS Code48Extension

Claude Code for VS Code: Harness the power of Claude Code without leaving your IDE

Compare →

@larksuiteoapi/lark-mcp

Capabilities8 decomposed

feishu/lark api resource exposure via mcp protocol

lark openapi schema-to-mcp tool translation

multi-tenant lark api credential management

lark document and knowledge base access via mcp

lark messaging and notification dispatch via mcp

lark calendar and event management via mcp

lark user and organization data access via mcp

mcp protocol compliance and client compatibility

Related Artifactssharing capabilities

@mseep/airylark-mcp-server

@ivotoby/openapi-mcp-server

Cloudflare MCP Server

4everland/4everland-hosting-mcp

@ivotoby/openapi-mcp-server

@iflow-mcp/figma-mcp

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Package Details

About

Categories

Alternatives to @larksuiteoapi/lark-mcp

Are you the builder of @larksuiteoapi/lark-mcp?

Get the weekly brief

Data Sources

@larksuiteoapi/lark-mcp

Capabilities8 decomposed

feishu/lark api resource exposure via mcp protocol

lark openapi schema-to-mcp tool translation

multi-tenant lark api credential management

lark document and knowledge base access via mcp

lark messaging and notification dispatch via mcp

lark calendar and event management via mcp

lark user and organization data access via mcp

mcp protocol compliance and client compatibility

Related Artifactssharing capabilities

@mseep/airylark-mcp-server

@ivotoby/openapi-mcp-server

Cloudflare MCP Server

4everland/4everland-hosting-mcp

@ivotoby/openapi-mcp-server

@iflow-mcp/figma-mcp

Best For

Known Limitations

Requirements

Input / Output

UnfragileRank

Package Details

About

Categories

Alternatives to @larksuiteoapi/lark-mcp

Are you the builder of @larksuiteoapi/lark-mcp?

Get the weekly brief

Data Sources