Lark (Feishu) API

Complete Lark/Feishu integration for enterprise collaboration, including messaging, group management, contacts, and calendar.

When to Use

• Send automated notifications to users or groups
• Build interactive bot workflows
• Manage group chats and members
• Query contacts and organization structure
• Sync calendar events and schedules
• Integrate Lark with other systems

Prerequisites

Set the following environment variables:

export LARK_APP_ID=cli_xxxxx
export LARK_APP_SECRET=xxxxx

Get your credentials from: https://open.larkoffice.com/

Required Permissions

Enable these API scopes in your Lark app:

• im:message - Send and read messages
• im:chat - Manage group chats
• contact:user.base:readonly - Read contacts
• calendar:calendar - Manage calendars

Token Management

Lark uses tenant access tokens that expire after 2 hours. Use this helper to get or refresh the token:

# Get or refresh token (cached to /tmp/lark_token.json)
get_lark_token() {
  local token_file="/tmp/lark_token.json"
  local current_time=$(date +%s)

  # Check if cached token is still valid
  if [ -f "$token_file" ]; then
    local expire_time=$(jq -r '.expire_time // 0' "$token_file" 2>/dev/null || echo "0")
    if [ "$current_time" -lt "$expire_time" ]; then
      jq -r '.tenant_access_token' "$token_file"
      return 0
    fi
  fi

  # Get new token
  local response=$(curl -s -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" \
    -H "Content-Type: application/json" \
    -d "{\"app_id\": \"${LARK_APP_ID}\", \"app_secret\": \"${LARK_APP_SECRET}\"}")

  local code=$(echo "$response" | jq -r '.code // -1')
  if [ "$code" != "0" ]; then
    echo "Error: $(echo "$response" | jq -r '.msg')" >&2
    return 1
  fi

  local expire=$(echo "$response" | jq -r '.expire')
  local expire_time=$((current_time + expire - 300))
  echo "$response" | jq ". + {expire_time: $expire_time}" > "$token_file"
  jq -r '.tenant_access_token' "$token_file"
}

# Usage in commands
TOKEN=$(get_lark_token)

Or get token directly without caching:

TOKEN=$(curl -s -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" \
  -H "Content-Type: application/json" \
  -d "{\"app_id\": \"$LARK_APP_ID\", \"app_secret\": \"$LARK_APP_SECRET\"}" | jq -r '.tenant_access_token')

Examples

1. Authentication - Get Access Token

Get and display tenant access token:

Write to /tmp/lark_request.json:

{
  "app_id": "${LARK_APP_ID}",
  "app_secret": "${LARK_APP_SECRET}"
}

curl -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

2. Messaging - Send Messages

Send Text Message to User

Write to /tmp/lark_request.json:

{
  "receive_id": "ou_xxx",
  "msg_type": "text",
  "content": "{\"text\": \"Hello World\"}"
}

TOKEN=$(get_lark_token)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=open_id" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

Send Text Message to Group Chat

Write to /tmp/lark_request.json:

{
  "receive_id": "oc_xxx",
  "msg_type": "text",
  "content": "{\"text\": \"Group message\"}"
}

TOKEN=$(get_lark_token)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

Send Rich Text (Post) Message

Write to /tmp/lark_request.json:

{
  "receive_id": "ou_xxx",
  "msg_type": "post",
  "content": "{\"zh_cn\": {\"title\": \"Title\", \"content\": [[{\"tag\": \"text\", \"text\": \"Content\"}]]}}"
}

TOKEN=$(get_lark_token)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=open_id" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

Send Interactive Card Message

Write to /tmp/lark_request.json:

{
  "receive_id": "oc_xxx",
  "msg_type": "interactive",
  "content": "{\"header\": {\"title\": {\"tag\": \"plain_text\", \"content\": \"Alert\"}}, \"elements\": [{\"tag\": \"div\", \"text\": {\"tag\": \"plain_text\", \"content\": \"Message\"}}]}"
}

TOKEN=$(get_lark_token)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

Reply to Message

Write to /tmp/lark_request.json:

{
  "msg_type": "text",
  "content": "{\"text\": \"Reply content\"}"
}

TOKEN=$(get_lark_token)
curl -X POST "https://open.feishu.cn/open-apis/im/v1/messages/om_xxx/reply" \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d @/tmp/lark_request.json

Get Chat History

TOKEN=$(get_lark_token)
how to use lark
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use lark on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add lark
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/vm0-ai/vm0-skills --skill larkcopy
The skills CLI fetches lark from GitHub repository vm0-ai/vm0-skills and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/lark
Reload or restart Cursor to activate lark. Access the skill through slash commands (e.g., /lark) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?