AI agents call get_congress_abstract_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 appears to be a prompt retrieval/generation service that provides expert guidance templates for medical writing tasks. It does not execute code, create or modify persistent data, delete anything, or move money. The action is purely informational—retrieving or generating a structured prompt for a user to follow.
From the tool's definition Tool name and description indicate it retrieves or generates a prompt template for drafting congress abstracts.
Attacks that exploit this kind of access
[PRO] Draft a congress abstract for ASCO, ASH, ESMO, APA, or similar. 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_congress_abstract_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_congress_abstract_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_congress_abstract_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_congress_abstract_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_congress_abstract_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 →