AI agents call get_analysis_card 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.
The tool name and context suggest this retrieves or queries an analysis card from the active MilliMap session without modifying data. The empty description creates some uncertainty, but the naming pattern and server context (listing, reading analyses) indicate a read-only operation. Assigned low severity due to read-only nature with no apparent side effects.
From the tool's definition Tool name 'get_analysis_card' suggests retrieval of analysis data; context from server description indicates it reads from MilliMap session (datasets, clusters, annotations, markers); tool description is empty but sibling tools include write/execute…
Attacks that exploit this kind of access
get_analysis_card. 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_analysis_card: 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_analysis_card 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_analysis_card 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_analysis_card. 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_analysis_card 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 →