AI agents use upload_dir to create or update resources in Nutstore — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nutstore environment.
This tool creates or modifies data in cloud storage by uploading directories and their contents. While it can overwrite existing files, it is reversible (files can be deleted or re-uploaded). It does not irreversibly destroy data like Destructive category tools, nor does it execute arbitrary code or move money.
From the tool's definition Tool name 'upload_dir' and description '将本机整个目录递归上传到坚果云(保留目录结构)' (recursively upload entire local directory to Nutstore while preserving directory structure) indicates file creation/modification in cloud storage.
Attacks that exploit this kind of access
将本机整个目录递归上传到坚果云(保留目录结构)。. It is categorised as a Write tool in the Nutstore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nutstore MCP server in PolicyLayer and add a rule for upload_dir: 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 Nutstore. Nothing to install.
upload_dir is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upload_dir 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.
Set action: deny in the PolicyLayer policy for upload_dir. 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.
upload_dir is provided by the Nutstore MCP server (silverze/nutstore-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →