// SCAN REPORT

Deepdepcat

31 tools. 23 can modify or destroy data without limits.

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

Last updated: 12 Aug 2026

23 can modify or destroy data

8 read-only

31 tools total

Community server · catalogue entry checked 06/08/2026

How to control Deepdepcat ↓

TOOL MAP

What Deepdepcat exposes to your agents

Read (8) Write / Execute (22) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Deepdepcat tools

Destructive · High writer_remove_content Irreversibly deletes document content items; cannot be undone without explicit restoration. Write · Low calc_add_sheet Creates reversible worksheet structure without data loss; low blast radius for spreadsheet operations. Write · Medium calc_merge_cells Merges cells in spreadsheet, modifying formatting and layout without deleting data. Write · Medium calc_set_cell Modifies spreadsheet cell values reversibly; no data deletion or financial impact.

23 of Deepdepcat's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Deepdepcat

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

Deny destructive operations

{
  "writer_remove_content": {
    "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

{
  "calc_add_sheet": {
    "limits": [
      {
        "counter": "calc_add_sheet_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "calc_get_cell": {
    "limits": [
      {
        "counter": "calc_get_cell_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 Deepdepcat — 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 DEEPDEPCAT →

Instant setup, no code required.

FULL CATALOGUE

All 31 Deepdepcat tools

DESTRUCTIVE 1 tools

Destructive writer_remove_content 【Writer】删除指定索引的内容项。index: 内容项索引（从0开始）。

WRITE 22 tools

Write calc_add_sheet 【Calc】添加新工作表。name: 工作表名称。 Write calc_merge_cells 合并单元格。 Write calc_set_cell 设置单元格。 Write calc_set_range 批量写入。 Write create_document 创建一个新的 WPS 文档项目。doc_type: writer(文字)/calc(表格)/impress(演示)。name: 文档名称。 Write export_document 导出文档。 Write impress_add_element 添加元素。 Write impress_add_slide 添加幻灯片。 Write impress_duplicate_slide 【Impress】复制幻灯片。index: 要复制的幻灯片索引。 Write impress_move_slide 移动幻灯片。 Write impress_set_slide_content 更新幻灯片。 Write open_document 打开已有的项目 JSON 文件。path: .json 项目文件路径。 Write redo 重做上一步撤销的操作。 Write save_document 保存当前文档项目到 JSON 文件。path: 保存路径（可选，默认原路径）。 Write undo 撤销上一步操作。 Write writer_add_heading 【Writer】添加标题。text: 标题文本，level: 1-6（1=H1, 2=H2...）。仅适用于 Writer 文档。 Write writer_add_image 添加图片。 Write writer_add_list 【Writer】添加列表。items: 列表项数组（如 [\ Write writer_add_page_break 【Writer】添加分页符。 Write writer_add_paragraph 【Writer】添加段落。text: 段落文本。可选 style: JSON 格式的样式（如 {\ Write writer_add_table 添加表格。 Write writer_find_replace 查找替换。

READ 8 tools

Read calc_get_cell 【Calc】获取单元格的值。ref: 单元格引用。sheet: 工作表索引。 Read calc_list_sheets 【Calc】列出所有工作表。 Read get_document_info 获取当前文档的信息摘要（类型、内容数量、工作表/幻灯片数等）。 Read get_session_status 获取会话状态（是否有文档、修改状态、撤销/重做计数）。 Read impress_list_slides 【Impress】列出所有幻灯片。 Read list_export_presets 列出所有可用的导出格式预设。 Read list_page_profiles 列出可用的页面配置文件（A4、Letter、16:9 等）。 Read writer_list_content 【Writer】列出所有内容项（含预览）。

EXPLORE

Related servers

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

FAQ

Questions about Deepdepcat

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

Yes. The Deepdepcat server exposes 1 destructive tools including writer_remove_content. 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 Deepdepcat? +

The Deepdepcat server has 22 write tools including calc_add_sheet, calc_merge_cells, calc_set_cell. 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 Deepdepcat.

How many tools does the Deepdepcat MCP server expose? +

31 tools across 3 categories: Destructive, Read, Write. 8 are read-only. 23 can modify, create, or delete data.

How do I enforce a policy on Deepdepcat? +

Register the Deepdepcat 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 Deepdepcat tool call.

Deterministic rules across all 31 Deepdepcat tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEEPDEPCAT →

Instant setup, no code required.

31 Deepdepcat tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Deepdepcat's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →