lark-cli

Official Lark/Feishu CLI tool, providing 200+ commands and 26 AI Agent Skills covering core business domains including Messenger, Docs, Base, Sheets, Slides, Calendar, Mail, Tasks, Meetings, and more. Designed for both human users and AI Agents who need to automate operations on the Lark/Feishu platform.

Use Cases

• Automate sending messages, creating calendar events, managing documents and spreadsheets
• Enable AI Agents to operate Lark/Feishu directly without manual login
• Batch process tasks, approvals, attendance, and OKR data
• Integrate into CI/CD pipelines or scripts for platform automation

Core Capabilities

How It Works

lark-cli provides a three-layer command system for different levels of granularity:

1. Shortcuts (prefixed with +): Human and AI friendly, with smart defaults, table output, and dry-run previews.
2. API Commands: Auto-generated from Lark OAPI metadata, curated through evaluation and quality gates — 100+ commands mapped 1:1 to platform endpoints.
3. Raw API Calls: Call any Lark Open Platform endpoint directly, covering 2500+ APIs.

After authentication, you can execute commands as a user or as a bot.

What You Need to Provide

• Node.js (when installing via npm/npx)
• Lark/Feishu app credentials: Configured via lark-cli config init (interactive guided setup)
• Login authorization: Complete OAuth login via lark-cli auth login and grant the required scopes

What You Get

• Operational access to all major Lark/Feishu business domains, including reading/writing data, managing resources, and executing automated workflows
• Multiple output formats: JSON (default), pretty, table, ndjson, CSV
• Advanced features: pagination, dry-run, schema introspection

Usage Examples

# View today's agenda
lark-cli calendar +agenda

# Send a message
lark-cli im +messages-send --chat-id "oc_xxx" --text "Hello"

# Create a document
lark-cli docs +create --doc-format markdown --content '<title>Weekly Report</title>\n# Progress\n- Completed feature X'

# Send message as bot
lark-cli im +messages-send --as bot --chat-id "oc_xxx" --text "Hello"

AI Agent Skills

26 structured Skills are included out of the box, compatible with popular AI tools — no extra setup needed. Selected Skills:

Important Notes

Security Risks: This tool can be invoked by AI Agents to automate operations on the Lark/Feishu Open Platform, carrying inherent risks such as model hallucinations, unpredictable execution, and prompt injection. After authorization, the AI Agent acts under your identity within the authorized scope, which may lead to high-risk consequences such as leakage of sensitive data or unauthorized operations. Use with caution.

• Default security protections are enabled at multiple layers. It is strongly recommended not to modify default security settings.
• It is recommended to use the integrated Lark/Feishu bot as a private conversational assistant. Do not add it to group chats or allow other users to interact with it.
• To reduce the security risks associated with access token theft, the CLI sends a minimal set of risk-control signals with OpenAPI requests made to exact official Feishu/Lark HTTPS domains. These signals are limited to operating system type (macOS, Windows, Linux) and device hardware model. This protection is enabled by default. To disable: lark-cli config risk-control off.

Authentication: Supports OAuth login with interactive selection or CLI flags for scopes. You can execute commands as user or bot.

Output Format: Default JSON. Success goes to stdout with exit code 0 and envelope { "ok": true, "identity": "...", "data": {...}, "meta": {...} }. Errors go to stderr with non-zero exit code and envelope { "ok": false, "identity": "...", "error": { "type": "...", "subtype": "...", "code": ..., "message": "...", "hint": "..." } }. To check success, test ok == true (or exit code) — not code == 0.

Pagination: Use --page-all for auto-pagination, --page-limit for max pages, --page-delay for delay between requests.

Dry Run: Preview requests with --dry-run before executing side-effect commands.

Schema Introspection: Use lark-cli schema to inspect any API method's parameters, request body, response structure, supported identities, and scopes.

This project is licensed under the MIT License. When running, it calls Lark/Feishu Open Platform APIs. Use of these APIs must comply with the applicable terms of service and privacy policies.