discourse_save_draft · Discourse MCP: Risk & Policy

WHAT IT DOES

What discourse_save_draft does on Discourse MCP

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

WHY IT NEEDS A POLICY

Why discourse_save_draft needs a policy

This tool creates or modifies draft content, which is a Write operation. It has low severity because: (1) drafts are not published/live, so blast radius is minimal; (2) changes are fully reversible (can be deleted via discourse_delete_draft); (3) no data is irreversibly destroyed or permanently exposed.

From the tool's definition Tool description states it can "Create a draft topic, create a draft reply, or update an existing draft." The use of verbs "create" and "update" indicate reversible modifications to data (drafts).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

discourse_save_draft Rate-limited

discourse_save_draft 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": {
    "discourse_save_draft": {
      "limits": [
        {
          "counter": "discourse_save_draft_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 Discourse MCP, so you can run agents against it safely.

FAQ

Questions about discourse_save_draft

What does the discourse_save_draft tool do? +

Create a draft topic, create a draft reply, or update an existing draft. Use this when the user wants to draft something without publishing immediately. For new topic drafts, use draft_key=. It is categorised as a Write tool in the Discourse MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on discourse_save_draft? +

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

What risk level is discourse_save_draft? +

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

Can I rate-limit discourse_save_draft? +

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

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

discourse_save_draft is provided by the Discourse MCP server (king-of-the-grackles/discourse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.