AI agents call get_capability_statement to retrieve information from Healow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a GET request to retrieve server capability metadata, which is a standard FHIR operation for discovering what resources and interactions a server supports. It is non-destructive, non-executable (no code/command execution), and non-financial. It is informational only, making it a Read category tool with low severity — misconfigured use poses minimal risk.
From the tool's definition Tool description states 'Fetch the server CapabilityStatement' — a read-only operation that retrieves metadata about the FHIR server's capabilities and conformance, with no side effects or data modification.
Attacks that exploit this kind of access
Fetch the server CapabilityStatement ({base}/metadata). It is categorised as a Read tool in the Healow MCP Server, which means it retrieves data without modifying state.
Register the Healow MCP server in PolicyLayer and add a rule for get_capability_statement: 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 Healow. Nothing to install.
get_capability_statement 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_capability_statement 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_capability_statement. 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_capability_statement is provided by the Healow MCP server (voysi-ia/healow-mcp-server). 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 →