AI agents call get_rebuttal_disagreement_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 Read category tool because it retrieves/generates prompt text without side effects. The severity is low because misuse would only result in potentially poorly-worded medical writing output, with no capability to modify systems, delete data, execute code, or cause financial harm. The tool is a template generator for professional writing tasks.
From the tool's definition Tool description states it generates a prompt to 'Draft a polite, evidence-based rebuttal' — this retrieves or composes text based on input parameters. No modification of external data, no code execution, no deletion, no financial transaction.
Attacks that exploit this kind of access
[PRO] Draft a polite, evidence-based rebuttal when disagreeing with a reviewer. 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_rebuttal_disagreement_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_rebuttal_disagreement_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_rebuttal_disagreement_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_rebuttal_disagreement_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_rebuttal_disagreement_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 →