AI agents call get_pub_plan_executive_summary_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 retrieves and returns a prompt template (a read operation). It has no side effects on data, does not execute code or external operations, does not create or modify records irreversibly, and does not involve financial transactions. The output is informational guidance for medical writing.
From the tool's definition Tool name includes 'get_prompt' pattern; description states it provides a 'one-page publication plan executive summary' — a template or guidance output for writing, with no data modification, deletion, code execution, or financial transaction.
Attacks that exploit this kind of access
[PRO] Write a one-page publication plan executive summary for medical affairs leadership. 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_pub_plan_executive_summary_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_pub_plan_executive_summary_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_pub_plan_executive_summary_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_pub_plan_executive_summary_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_pub_plan_executive_summary_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 →