Retrieves an AI-generated summary from a patient
AI agents call getSummaryFromFHIR to retrieve information from Jokes MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves (queries) patient summary data without modifying, deleting, or executing external operations. However, severity is elevated to medium rather than low because this involves sensitive healthcare data (FHIR is a healthcare data standard), creating privacy and compliance concerns if misused by an agent.
From the tool's definition Tool name is 'getSummaryFromFHIR' and description states it 'Retrieves an AI-generated summary from a patient' — uses 'Retrieves' indicating read-only data access, not modification or deletion.
Attacks that exploit this kind of access
Retrieves an AI-generated summary from a patient. It is categorised as a Read tool in the Jokes MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jokes MCP Server MCP server in PolicyLayer and add a rule for getSummaryFromFHIR: 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 Jokes MCP Server. Nothing to install.
getSummaryFromFHIR 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 getSummaryFromFHIR 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 getSummaryFromFHIR. 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.
getSummaryFromFHIR is provided by the Jokes MCP Server MCP server (shekhar-ai99/clinical-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 →