prompthub_upload_reference · Prompthub MCP: Risk & Policy

WHAT IT DOES

What prompthub_upload_reference does on Prompthub

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

WHY IT NEEDS A POLICY

Why prompthub_upload_reference needs a policy

This tool creates new reference assets by uploading files and associating them with prompt units. This is a reversible modification (references can be deleted via sibling tool prompthub_delete_reference), making it Write rather than Destructive.

From the tool's definition Tool uploads and binds a local file as a reference asset to a prompt unit. The description states 'Upload a local file' and 'bound to a prompt unit,' indicating it creates or modifies data structures within PromptHub repositories.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prompthub_upload_reference Rate-limited

prompthub_upload_reference 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": {
    "prompthub_upload_reference": {
      "limits": [
        {
          "counter": "prompthub_upload_reference_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 Prompthub, so you can run agents against it safely.

FAQ

Questions about prompthub_upload_reference

What does the prompthub_upload_reference tool do? +

Upload a local file as a PromptReference input asset, bound to a prompt unit. This is NOT a generated artifact. Set filePath to an existing repo file path; targetKind is TEXT_FILE, WORKFLOW_NODE, or CONVERSATION_TURN. targetId is required for node/turn targets. See prompthub_describe_reference_format. It is categorised as a Write tool in the Prompthub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prompthub_upload_reference? +

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

What risk level is prompthub_upload_reference? +

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

Can I rate-limit prompthub_upload_reference? +

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

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

prompthub_upload_reference is provided by the Prompthub MCP server (lionelhao/prompthub-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.