retrieve_dicom_instances
AI agents call retrieve_dicom_instances to retrieve information from DICOM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves DICOM medical imaging instances from a PACS/VNA server. While the description is empty, the name and server context indicate a read operation that fetches existing data without side effects.
From the tool's definition Tool name 'retrieve_dicom_instances' combined with server description stating 'query, read, download, and move medical imaging data' and sibling tools like 'query_patients', 'query_studies', 'query_series' that are clearly read operations.
Attacks that exploit this kind of access
retrieve_dicom_instances. It is categorised as a Read tool in the DICOM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the DICOM MCP Server MCP server in PolicyLayer and add a rule for retrieve_dicom_instances: 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 DICOM MCP Server. Nothing to install.
retrieve_dicom_instances 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 retrieve_dicom_instances 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 retrieve_dicom_instances. 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.
retrieve_dicom_instances is provided by the DICOM MCP Server MCP server (y5ive9ine/dicom-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 →