AI agents call get_speaker_notes_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 or generates a prompt template to help structure speaker notes. It is a read operation — it queries the toolkit's knowledge base and returns formatted text content without modifying any underlying data, creating records in databases, or triggering external processes.
From the tool's definition Tool description states 'Write speaker notes for a data slide' — it generates text content (speaker notes) based on a prompt/template. The verb 'write' here refers to content generation/retrieval of a prompt template, not data modification.
Attacks that exploit this kind of access
[PRO] Write speaker notes for a data slide. 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_speaker_notes_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_speaker_notes_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_speaker_notes_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_speaker_notes_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_speaker_notes_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 →