AI agents call get_binary 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 retrieves binary data (likely medical documents or images) by identifier from a FHIR R4 API. It performs a GET-like operation with no capability to modify, delete, or execute actions. The sensitivity is tempered by the fact that access control and authentication (handled by connect_practice and complete_oauth) are prerequisites, limiting the blast radius of accidental misuse.
From the tool's definition Tool name 'get_binary' and description 'Fetch a Binary by id as {content_type, data_base64}' indicate retrieval of existing data. The verb 'Fetch' and read-only operation confirm no modification or side effects occur.
Attacks that exploit this kind of access
Fetch a Binary by id as {content_type, data_base64}. 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_binary: 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_binary 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_binary 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_binary. 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_binary 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 →