Medium Risk

write_docx_content

向飞书云文档写入 Markdown 内容。将 Markdown 解析为飞书文档块(标题、列表、代码块、引用等),追加到文档末尾。适用于向已有文档批量写入结构化内容

How to control write_docx_content ↓

What write_docx_content does on Personal Knowledge MCP Server

AI agents use write_docx_content to create or update resources in Personal Knowledge MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Personal Knowledge MCP Server environment.

Medium Risk

Why write_docx_content needs a policy

This tool creates or modifies data in cloud documents (Feishu) by appending Markdown content. It falls squarely into the Write category: it changes document state (adds content) but is reversible—appended content can be deleted and the document restored to a previous state.

From the tool's definition Tool description explicitly states '向飞书云文档写入' (write to Feishu cloud documents) and 'Markdown 解析为飞书文档块...追加到文档末尾' (parse Markdown into Feishu document blocks and append to document end).

Documented attack patterns abuse exactly the kind of access write_docx_content gives an agent:

How to control write_docx_content

PolicyLayer is an MCP gateway — it sits between your AI agents and Personal Knowledge MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for write_docx_content:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "write_docx_content": {
      "limits": [
        {
          "counter": "write_docx_content_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

write_docx_content stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Personal Knowledge MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about write_docx_content

What does the write_docx_content tool do? +

向飞书云文档写入 Markdown 内容。将 Markdown 解析为飞书文档块(标题、列表、代码块、引用等),追加到文档末尾。适用于向已有文档批量写入结构化内容. It is categorised as a Write tool in the Personal Knowledge MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on write_docx_content? +

Register the Personal Knowledge MCP Server MCP server in PolicyLayer and add a rule for write_docx_content: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Personal Knowledge MCP Server. Nothing to install.

What risk level is write_docx_content? +

write_docx_content is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit write_docx_content? +

Yes. Add a rate_limit block to the write_docx_content rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block write_docx_content completely? +

Set action: deny in the PolicyLayer policy for write_docx_content. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides write_docx_content? +

write_docx_content is provided by the Personal Knowledge MCP Server MCP server (kyodule/personal-knowledge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Personal Knowledge MCP Server tool call.

Start from Personal Knowledge MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

29 Personal Knowledge MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.