prompthub_publish_artifact · Prompthub MCP: Risk & Policy

WHAT IT DOES

What prompthub_publish_artifact does on Prompthub

AI agents use prompthub_publish_artifact 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_publish_artifact needs a policy

The tool creates or modifies data in a reversible manner by publishing artifacts to a repository. This is a classic Write operation—content can be updated, overwritten, or removed via other tools (e.g., prompthub_delete_artifact).

From the tool's definition Tool description states 'Publish a GENERATED text RESULT' which involves creating/storing content in a repository. The 256 KiB size limit and format restrictions (Markdown or HTML) indicate it writes data to a persistent storage system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prompthub_publish_artifact Rate-limited

prompthub_publish_artifact 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_publish_artifact": {
      "limits": [
        {
          "counter": "prompthub_publish_artifact_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_publish_artifact

What does the prompthub_publish_artifact tool do? +

Publish a GENERATED text RESULT (Markdown or HTML, ≤256 KiB) to a repo. 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_publish_artifact? +

Register the Prompthub MCP server in PolicyLayer and add a rule for prompthub_publish_artifact: 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_publish_artifact? +

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

Can I rate-limit prompthub_publish_artifact? +

Yes. Add a rate_limit block to the prompthub_publish_artifact 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_publish_artifact completely? +

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

prompthub_publish_artifact 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.