AI agents call get_cmpp_practice_questions_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 tool produces educational content (practice exam questions) and returns it to the user. No data is created in external systems, no code is executed, no resources are modified or deleted, and no financial transactions occur. It is a straightforward read operation—fetching or generating informational content for display.
From the tool's definition Tool generates and retrieves CMPP certification exam practice questions with explanations—a content generation/retrieval operation with no side effects.
Attacks that exploit this kind of access
[PRO] Generate CMPP certification exam practice questions with explanations. 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_cmpp_practice_questions_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_cmpp_practice_questions_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_cmpp_practice_questions_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_cmpp_practice_questions_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_cmpp_practice_questions_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 →