AI agents call get_slide_deck_outline_prompt to retrieve information from Medwriter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a prompt generation utility that synthesizes and returns medical writing guidance. It reads input parameters and outputs formatted text/templates for pharmaceutical educational materials. There is no creation of persistent data, modification of systems, execution of code, or any irreversible action. The 'PRO' designation indicates premium content access, not elevated risk.
From the tool's definition Tool returns a prompt/outline template ('Create a slide-by-slide outline') — it retrieves and formats informational content with no side effects, data modification, code execution, or destructive actions.
Attacks that exploit this kind of access
[PRO] Create a slide-by-slide outline for advisory board, symposium, or HCP education decks. It is categorised as a Read tool in the Medwriter MCP Server, which means it retrieves data without modifying state.
Register the Medwriter MCP server in PolicyLayer and add a rule for get_slide_deck_outline_prompt: 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 Medwriter. Nothing to install.
get_slide_deck_outline_prompt 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 get_slide_deck_outline_prompt 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 get_slide_deck_outline_prompt. 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.
get_slide_deck_outline_prompt is provided by the Medwriter MCP server (pubspro/medwriter-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 →