html_upload_file · Llama MCP: Risk & Policy

WHAT IT DOES

What html_upload_file does on Llama

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

WHY IT NEEDS A POLICY

Why html_upload_file needs a policy

This tool uploads HTML files to the Llama Ventures platform, creating or adding content. The 'upload' operation is a Write action—it modifies platform state by adding data. Severity is medium rather than high because uploads to a managed platform are typically gated and reversible (context shows brief_delete exists). The tool is agent-safe according to its description, suggesting guardrails are in place.

From the tool's definition html_upload_file: Agent-safe HTML upload from a LOCAL FILE PATH.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

html_upload_file Rate-limited

html_upload_file 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": {
    "html_upload_file": {
      "limits": [
        {
          "counter": "html_upload_file_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 Llama, so you can run agents against it safely.

FAQ

Questions about html_upload_file

What does the html_upload_file tool do? +

Agent-safe HTML upload from a LOCAL FILE PATH. Use this instead. It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on html_upload_file? +

Register the Llama MCP server in PolicyLayer and add a rule for html_upload_file: 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 Llama. Nothing to install.

What risk level is html_upload_file? +

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

Can I rate-limit html_upload_file? +

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

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

html_upload_file is provided by the Llama MCP server (llama-ventures/llama-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.