List a patient's observations. reason is audited.
AI agents call list_observations to retrieve information from Fhir Synthetic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries patient observation data without any side effects. Even though the `reason` is audited, the core function is retrieving existing data. The audit mechanism is a governance control, not an indication of write or destructive capability. This is clearly a Read category tool with low severity since misuse would only expose sensitive health information rather than modify or delete it.
From the tool's definition Tool name 'list_observations' and description 'List a patient's observations' indicate data retrieval with no modification. The `reason` parameter for audit purposes confirms this is a read operation.
Attacks that exploit this kind of access
List a patient's observations. reason is audited. It is categorised as a Read tool in the Fhir Synthetic MCP Server, which means it retrieves data without modifying state.
Register the Fhir Synthetic MCP server in PolicyLayer and add a rule for list_observations: 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 Fhir Synthetic. Nothing to install.
list_observations 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 list_observations 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 list_observations. 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.
list_observations is provided by the Fhir Synthetic MCP server (krishnakakani-github/fhir-synthetic-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 →