AI agents call load-dicom-seg 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.
This tool retrieves and processes an existing DICOM SEG (segmentation) file and links it to another image in memory. It performs a read operation with no side effects—no data is created, modified, deleted, or executed. The file association is a logical operation performed within the application context, not a persistent write to the source data.
From the tool's definition The tool 'load-dicom-seg' is described as loading a DICOM SEG file and associating it with a reference image. The verb 'load' and the action of 'associating' indicate data retrieval and in-memory pairing operations without modification of underlying data.
Attacks that exploit this kind of access
Load a DICOM SEG file and associate it with a reference image. 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-seg: 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-seg 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-seg 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-seg. 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-seg 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 →