// SCAN REPORT

Feishu MCP Server

18 tools. 13 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

13 can modify or destroy data

5 read-only

18 tools total

Community server · catalogue entry verified 30/06/2026

How to control Feishu MCP Server ↓

TOOL MAP

What Feishu MCP Server exposes to your agents

Read (5) Write / Execute (12) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Feishu MCP Server tools

Destructive · High feishu_delete_block The tool is designed to irreversibly remove content blocks from Feishu documents. Write · Medium feishu_add_bitable_records This tool creates new records in a Feishu multi-dimensional table (bitable), which is a reversible write operation. Write · Medium feishu_append_content This tool creates or modifies data (appends content to documents) in a reversible manner. Write · Medium feishu_create_bitable This tool creates a new multi-dimensional table/spreadsheet in Feishu, which is a reversible Write operation.

13 of Feishu MCP Server's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Feishu MCP Server

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

Deny destructive operations

{
  "feishu_delete_block": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "feishu_add_bitable_records": {
    "limits": [
      {
        "counter": "feishu_add_bitable_records_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "feishu_get_document_info": {
    "limits": [
      {
        "counter": "feishu_get_document_info_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 Feishu MCP Server — 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 FEISHU →

Instant setup, no code required.

FULL CATALOGUE

All 18 Feishu MCP Server tools

DESTRUCTIVE 1 tools

Destructive feishu_delete_block 删除飞书文档中的指定 Block。⚠️ 注意：当前飞书 API 可能不支持直接删除文档块，此功能可能无法使用。建议通过编辑将块内容清空作为替代方案。

WRITE 12 tools

Write feishu_add_bitable_records 向飞书多维表格添加记录。字段名需与表格字段名一致。 Write feishu_append_content 向飞书文档末尾追加内容。支持 Markdown 格式，包括标题、列表、代码块、表格等。 Write feishu_create_bitable 创建新的飞书多维表格（Bitable）。返回 app_token 和 URL。 Write feishu_create_document 创建新的飞书文档。可以指定标题和 Markdown 格式的内容，返回新文档的 URL。 Write feishu_create_spreadsheet 创建新的飞书电子表格。返回电子表格的 Token 和 URL。 Write feishu_insert_callout 在飞书文档中插入高亮块（Callout）。用于突出显示提示、警告、注意事项等信息。 Write feishu_insert_diagram 在飞书文档中插入 Mermaid 架构图（使用飞书「文本绘图」功能）。支持 flowchart、sequenceDiagram、classDiagram、graph、mindmap、timeline 等类型。 Write feishu_insert_image 在飞书文档中插入图片。支持通过文件 token 插入已上传的图片。 Write feishu_insert_table 在飞书文档中插入表格。支持 Markdown 表格语法或结构化数据输入。 Write feishu_update_content 替换飞书文档的全部内容（保留标题）。用于完全重写文档内容。 Write feishu_upload_image 上传图片到飞书。返回 file_token，可用于 feishu_insert_image 插入文档。⚠️ 需要 drive:drive:media:upload 权限。 Write feishu_write_spreadsheet 向飞书电子表格写入数据。支持指定工作表和范围。

READ 5 tools

Read feishu_get_document_info 获取飞书文档的基本信息，包括标题、ID、版本号等。 Read feishu_list_blocks 列出飞书文档中的所有 Block，用于了解文档结构或获取特定 Block ID 进行后续操作。 Read feishu_read_bitable 读取飞书多维表格的记录。返回 Markdown 格式的表格。 Read feishu_read_document 读取飞书文档内容。支持输入文档 ID 或完整 URL，返回 Markdown 或 JSON 格式的文档内容。 Read feishu_read_spreadsheet 从飞书电子表格读取数据。返回指定范围的数据。

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Feishu MCP Server

Can an AI agent delete data through the Feishu MCP Server MCP server? +

Yes. The Feishu MCP Server server exposes 1 destructive tools including feishu_delete_block. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Feishu MCP Server? +

The Feishu MCP Server server has 12 write tools including feishu_add_bitable_records, feishu_append_content, feishu_create_bitable. 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 Feishu MCP Server.

How many tools does the Feishu MCP Server MCP server expose? +

18 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 13 can modify, create, or delete data.

How do I enforce a policy on Feishu MCP Server? +

Register the Feishu MCP Server 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 Feishu MCP Server tool call.

Deterministic rules across all 18 Feishu MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FEISHU →

Instant setup, no code required.

18 Feishu MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.