AI agents call get_strengthen_conclusions_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 an expert prompt to assist with medical writing. It generates or returns instructional content to help rewrite text, but does not create, modify, delete, or execute operations on external systems. The output is read-only guidance. Even if used to generate suggested text, the tool itself performs no side effects—it merely provides a prompt/template for a user's subsequent action.
From the tool's definition Tool is named 'get_strengthen_conclusions_prompt' and description states it will 'Rewrite an abstract conclusion' — this is a retrieval of a prompt template/guidance.
Attacks that exploit this kind of access
[PRO] Rewrite an abstract conclusion to be data-anchored and clinically meaningful. 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_strengthen_conclusions_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_strengthen_conclusions_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_strengthen_conclusions_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_strengthen_conclusions_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_strengthen_conclusions_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 →