AI agents use apply_qc_filter to create or update resources in Millimap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Millimap environment.
Applying QC filters is a reversible data transformation that changes the active dataset's configuration or visibility. It is not destructive (filters can be removed/adjusted), not financial, and not execute-class (it doesn't run arbitrary code or commands). It modifies state, making it Write.
From the tool's definition Tool description states 'Apply QC filters to the active dataset in MilliMap' — this modifies the dataset state by applying quality-control filters, which changes what data is visible/active without irreversibly deleting records.
Attacks that exploit this kind of access
Apply QC filters to the active dataset in MilliMap. It is categorised as a Write tool in the Millimap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Millimap MCP server in PolicyLayer and add a rule for apply_qc_filter: 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.
apply_qc_filter is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the apply_qc_filter 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 apply_qc_filter. 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.
apply_qc_filter 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 →