cli

lark-cli

中文版 | English

The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Slides, Calendar, Mail, Tasks, Meetings, Markdown, and more, with 200+ commands and 26 AI Agent Skills.

Install · AI Agent Skills · Auth · Commands · Advanced · Security · Contributing

Why lark-cli?

• Agent-Native Design — 24 structured Skills out of the box, compatible with popular AI tools — Agents can operate Lark with zero extra setup
• Wide Coverage — 18 business domains, 200+ curated commands, 26 AI Agent Skills
• AI-Friendly & Optimized — Every command is tested with real Agents, featuring concise parameters, smart defaults, and structured output to maximize Agent call success rates
• Open Source, Zero Barriers — MIT license, ready to use, just npm install
• Up and Running in 3 Minutes — One-click app creation, interactive login, from install to first API call in just 3 steps
• Secure & Controllable — Input injection protection, terminal output sanitization, OS-native keychain credential storage
• Three-Layer Architecture — Shortcuts (human & AI friendly) → API Commands (platform-synced) → Raw API (full coverage), choose the right granularity

Features

Installation & Quick Start

Requirements

Before you start, make sure you have:

• Node.js (npm/npx)
• Go v1.23+ and Python 3 (only required for building from source)

Quick Start (Human Users)

Note for AI assistants: If you are an AI Agent helping the user with installation, jump directly to Quick Start (AI Agent), which contains all the steps you need to complete.

Install

Choose one of the following methods:

Option 1 — From npm (recommended):

npx @larksuite/cli@latest install

Option 2 — From source:

Requires Go v1.23+ and Python 3.

git clone https://github.com/larksuite/cli.git
cd cli
make install

# Install CLI SKILL (required)
npx skills add larksuite/cli -y -g

Configure & Use

# 1. Configure app credentials (one-time, interactive guided setup)
lark-cli config init

# 2. Log in (--recommend auto-selects commonly used scopes)
lark-cli auth login --recommend

# 3. Start using
lark-cli calendar +agenda

Quick Start (AI Agent)

The following steps are for AI Agents. Some steps require the user to complete actions in a browser.

Step 1 — Install

npx @larksuite/cli@latest install

Step 2 — Configure app credentials

Run this command in the background. It will output an authorization URL — extract it and send it to the user. The command exits automatically after the user completes the setup in the browser.

lark-cli config init --new

Step 3 — Login

Same as above: run in the background, extract the authorization URL and send it to the user.

lark-cli auth login --recommend

Step 4 — Verify

lark-cli auth status

Agent Skills

Authentication

# Interactive login (TUI guides domain and permission level selection)
lark-cli auth login

# Filter by domain
lark-cli auth login --domain calendar,task

# Recommended auto-approval scopes
lark-cli auth login --recommend

# Exact scope
lark-cli auth login --scope "calendar:calendar:read"

# Agent mode: return verification URL immediately, non-blocking
lark-cli auth login --domain calendar --no-wait
# Resume polling later
lark-cli auth login --device-code <DEVICE_CODE>

# Identity switching: execute commands as user or bot
lark-cli calendar +agenda --as user
lark-cli im +messages-send --as bot --chat-id "oc_xxx" --text "Hello"

Three-Layer Command System

The CLI provides three levels of granularity, covering everything from quick operations to fully custom API calls:

1. Shortcuts

Prefixed with +, designed to be friendly for both humans and AI, with smart defaults, table output, and dry-run previews.

lark-cli calendar +agenda
lark-cli im +messages-send --chat-id "oc_xxx" --text "Hello"
lark-cli docs +create --doc-format markdown --content $'<title>Weekly Report</title>\n# Progress\n- Completed feature X'

Run lark-cli <service> --help to see all shortcut commands.

2. API Commands

Auto-generated from Lark OAPI metadata, curated through evaluation and quality gates — 100+ commands mapped 1:1 to platform endpoints.

lark-cli calendar calendars list
lark-cli calendar events instance_view --params '{"calendar_id":"primary","start_time":"1700000000","end_time":"1700086400"}'

3. Raw API Calls

Call any Lark Open Platform endpoint directly, covering 2500+ APIs.

lark-cli api GET /open-apis/calendar/v4/calendars
lark-cli api POST /open-apis/im/v1/messages --params '{"receive_id_type":"chat_id"}' --data '{"receive_id":"oc_xxx","msg_type":"text","content":"{\"text\":\"Hello\"}"}'

Advanced Usage

Output Formats

--format json      # Full JSON response (default)
--format pretty    # Human-friendly formatted output
--format table     # Readable table
--format ndjson    # Newline-delimited JSON (for piping)
--format csv       # Comma-separated values

JSON Output Contract

With --format json (the default), success and error envelopes are distinct.

Success goes to stdout, exit code 0:

{ "ok": true, "identity": "user", "data": { "guid": "..." }, "meta": { "count": 1 } }

Errors go to stderr, non-zero exit code:

{ "ok": false, "identity": "user", "error": { "type": "api", "subtype": "...", "code": 99991679, "message": "...", "hint": "..." } }

To check whether a command succeeded, test ok == true (or the exit code) — not code == 0. Unlike raw OpenAPI responses ({"code": 0, "msg": "ok", ...}), the success envelope carries no code or msg field; code appears only inside error as the upstream OpenAPI code. See errs/ERROR_CONTRACT.md for the full error taxonomy.

Pagination

--page-all                  # Auto-paginate through all pages
--page-limit 5              # Max 5 pages
--page-delay 500            # 500ms between page requests

Dry Run

For commands that may have side effects, preview the request with --dry-run first:

lark-cli im +messages-send --chat-id oc_xxx --text "hello" --dry-run

Schema Introspection

Use schema to inspect any API method's parameters, request body, response structure, supported identities, and scopes:

lark-cli schema
lark-cli schema calendar.events.instance_view
lark-cli schema im.messages.delete

Security & Risk Warnings (Read Before Use)

This tool can be invoked by AI Agents to automate operations on the Lark/Feishu Open Platform, and carries inherent risks such as model hallucinations, unpredictable execution, and prompt injection. After you authorize Lark/Feishu permissions, the AI Agent will act under your user identity within the authorized scope, which may lead to high-risk consequences such as leakage of sensitive data or unauthorized operations. Please use with caution.

To reduce these risks, the tool enables default security protections at multiple layers. However, these risks still exist. We strongly recommend that you do not proactively modify any default security settings; once relevant restrictions are relaxed, the risks will increase significantly, and you will bear the consequences.

We recommend using the Lark/Feishu bot integrated with this tool as a private conversational assistant. Do not add it to group chats or allow other users to interact with it, to avoid abuse of permissions or data leakage.

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 used to help identify anomalous API activity. This protection is enabled by default. The information sent is limited to:

• Operating system type: macOS, Windows, or Linux
• Device hardware model: for example, Mac17,9

To disable this protection for the current workspace, run:

lark-cli config risk-control off

To enable this protection for the current workspace, run:

lark-cli config risk-control on

To restore the default policy for the current workspace, run:

lark-cli config risk-control default

Please fully understand all usage risks. By using this tool, you are deemed to voluntarily assume all related responsibilities.

Contributing

Community contributions are welcome! If you find a bug or have feature suggestions, please submit an Issue or Pull Request.

For major changes, we recommend discussing with us first via an Issue.

Before opening a PR, see AGENTS.md for the local build, test, and PR checklist used by contributors and AI agents.

License

This project is licensed under the MIT License. When running, it calls Lark/Feishu Open Platform APIs. To use these APIs, you must comply with the following agreements and privacy policies:

• Feishu User Terms of Service
• Feishu Privacy Policy
• Feishu Open Platform App Service Provider Security Management Specifications
• Lark User Terms of Service
• Lark Privacy Policy