yuque_multipart_request · Yuque Mcp Plus MCP: Risk & Policy

WHAT IT DOES

What yuque_multipart_request does on Yuque Mcp Plus

AI agents use yuque_multipart_request to create or update resources in Yuque Mcp Plus — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Yuque Mcp Plus environment.

WHY IT NEEDS A POLICY

Why yuque_multipart_request needs a policy

Multipart requests are typically used for uploading files and creating new data structures. While uploads don't typically meet the 'destructive' threshold, the generic nature of this endpoint alongside sibling deletion tools (yuque_delete_doc, yuque_delete_repo, yuque_delete_toc_node) and the ability to potentially overwrite attachments elevates this to Write category with high severity.

From the tool's definition Tool description indicates 'multipart request for upload-style endpoints' which creates or modifies data in Yuque; the generic nature of 'multipart request' combined with 'attachment workflows' suggests file uploads and data creation/modification capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

yuque_multipart_request Rate-limited

yuque_multipart_request 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "yuque_multipart_request": {
      "limits": [
        {
          "counter": "yuque_multipart_request_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Yuque Mcp Plus, so you can run agents against it safely.

FAQ

Questions about yuque_multipart_request

What does the yuque_multipart_request tool do? +

Generic Yuque multipart request for upload-style endpoints such as attachment workflows. It is categorised as a Write tool in the Yuque Mcp Plus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on yuque_multipart_request? +

Register the Yuque Mcp Plus MCP server in PolicyLayer and add a rule for yuque_multipart_request: 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 Yuque Mcp Plus. Nothing to install.

What risk level is yuque_multipart_request? +

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

Can I rate-limit yuque_multipart_request? +

Yes. Add a rate_limit block to the yuque_multipart_request 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 yuque_multipart_request completely? +

Set action: deny in the PolicyLayer policy for yuque_multipart_request. 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 yuque_multipart_request? +

yuque_multipart_request is provided by the Yuque Mcp Plus MCP server (michealjou/yuque-mcp-plus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.