AI agents call load-dicom-series to retrieve information from DICOM-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Loading data into memory for processing is a read-only operation. It retrieves DICOM medical image data but does not create, modify, delete, or execute operations. While medical data is sensitive, the tool itself performs no destructive or irreversible actions. No side effects beyond memory consumption occur.
From the tool's definition Tool name is 'load-dicom-series' and description states it 'Load[s] a DICOM series into memory for processing' — this is a data retrieval operation with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Load a DICOM series into memory for processing. It is categorised as a Read tool in the DICOM-MCP MCP Server, which means it retrieves data without modifying state.
Register the DICOM- MCP server in PolicyLayer and add a rule for load-dicom-series: 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. Nothing to install.
load-dicom-series 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 load-dicom-series 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 load-dicom-series. 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.
load-dicom-series is provided by the DICOM- MCP server (shaunporwal/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 →