AI agents call get_cluster_markers to retrieve information from Millimap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data (marker genes) from an existing cluster analysis. It performs a read-only retrieval operation without creating, modifying, deleting, or executing any external operations. The action is informational and has no adverse side effects if misused by an agent.
From the tool's definition Tool name 'get_cluster_markers' and description 'Return top marker genes for a specific cluster' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Return top marker genes for a specific cluster. It is categorised as a Read tool in the Millimap MCP Server, which means it retrieves data without modifying state.
Register the Millimap MCP server in PolicyLayer and add a rule for get_cluster_markers: 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 Millimap. Nothing to install.
get_cluster_markers 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_cluster_markers 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_cluster_markers. 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_cluster_markers is provided by the Millimap MCP server (milliomics/millimap-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 →