Retrieve a specific draft by its key. Common keys:
AI agents call discourse_get_draft to retrieve information from Discourse MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches an existing draft without creating, modifying, deleting, or executing any operations. It is purely a read operation that queries data. The severity is low because retrieving a draft has minimal blast radius—it only exposes data that the authenticated user already has access to.
From the tool's definition Tool name 'discourse_get_draft' and description 'Retrieve a specific draft' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieve a specific draft by its key. Common keys:. It is categorised as a Read tool in the Discourse MCP MCP Server, which means it retrieves data without modifying state.
Register the Discourse MCP server in PolicyLayer and add a rule for discourse_get_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.
discourse_get_draft is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the discourse_get_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.
Set action: deny in the PolicyLayer policy for discourse_get_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.
discourse_get_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.
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 →