// SCAN REPORT

Lark Cli

19 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

5 can modify or destroy data

14 read-only

19 tools total

Community server · catalogue entry verified 02/07/2026

How to control Lark Cli ↓

TOOL MAP

What Lark Cli exposes to your agents

Read (14) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Lark Cli tools

Write · High feishu_base_record_upsert The tool modifies data in Feishu's base/table system by either creating new records or updating existing ones. Write · Medium feishu_doc_create This tool creates new documents in Feishu, which is a reversible write operation. Write · High feishu_doc_update This tool creates or modifies data reversibly by updating document content. Write · High feishu_send_message This tool sends messages on behalf of the user to groups or individuals.

5 of Lark Cli's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Lark Cli

PolicyLayer is an MCP gateway — it sits between your AI agents and Lark Cli, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "feishu_base_record_upsert": {
    "limits": [
      {
        "counter": "feishu_base_record_upsert_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "feishu_base_field_list": {
    "limits": [
      {
        "counter": "feishu_base_field_list_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Lark Cli — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON LARK CLI →

Instant setup, no code required.

FULL CATALOGUE

All 19 Lark Cli tools

WRITE 5 tools

Write feishu_base_record_upsert 在多维表格数据表中创建或更新一条记录（给 record_id 则更新，否则创建） Write feishu_doc_create 新建一篇飞书文档（Markdown 内容） Write feishu_doc_update 更新一篇飞书文档内容 Write feishu_reply_message 回复某条飞书消息（支持线程回复） Write feishu_send_message 以用户身份发送飞书/Lark 消息到群聊或个人（支持纯文本与 Markdown）

READ 14 tools

Read feishu_base_field_list 列出多维表格某个数据表的字段（列） Read feishu_base_record_list 列出多维表格某个数据表的记录（行），支持筛选/排序 Read feishu_base_record_search 在多维表格数据表中检索记录 Read feishu_base_table_list 列出某个多维表格（Bitable/Base）下的所有数据表 Read feishu_doc_fetch 读取一篇飞书文档的内容（传文档 URL 或 token） Read feishu_drive_search 在云盘中搜索文件（doc/sheet/bitable/file 等），支持类型筛选 Read feishu_get_messages 查看群聊或私聊的最近消息记录 Read feishu_get_thread 查看某条消息的完整线程讨论 Read feishu_list_chats 搜索飞书群聊列表（按关键词找 chat_id） Read feishu_search_docs 搜索飞书云文档（文档/Wiki/表格），按关键词。返回标题、token、URL 等 Read feishu_search_messages 跨群搜索飞书消息（用户身份） Read feishu_search_user 按名字/邮箱搜索飞书用户，拿到 open_id Read feishu_wiki_node_get 读取一个 Wiki 节点详情（支持传 Lark URL / node_token / obj_token） Read feishu_wiki_node_list 列出某个 Wiki 空间或父节点下的节点

FAQ

Questions about Lark Cli

How do I prevent bulk modifications through Lark Cli? +

The Lark Cli server has 5 write tools including feishu_base_record_upsert, feishu_doc_create, feishu_doc_update. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Lark Cli.

How many tools does the Lark Cli MCP server expose? +

19 tools across 2 categories: Read, Write. 14 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Lark Cli? +

Register the Lark Cli MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Lark Cli tool call.

Deterministic rules across all 19 Lark Cli tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON LARK CLI →

Instant setup, no code required.

19 Lark Cli tools catalogued and risk-classified — across an index of 43,000+ MCP servers.