AI agents call qaradar_churn to retrieve information from QA Radar 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 read-only analytical information about file change frequency and regression hotspots. It has no side effects, does not modify any data, and only surfaces existing metrics. Misuse risk is minimal as it only exposes repository churn statistics.
From the tool's definition 'asks which files change most often, what the hotspots are, or where regressions tend to occur' — purely retrieves and reports analytical data about file churn history
Attacks that exploit this kind of access
Use when the user asks which files change most often, what the hotspots are, or where regressions tend to occur. It is categorised as a Read tool in the QA Radar MCP Server, which means it retrieves data without modifying state.
Register the QA Radar MCP server in PolicyLayer and add a rule for qaradar_churn: 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 QA Radar. Nothing to install.
qaradar_churn 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 qaradar_churn 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 qaradar_churn. 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.
qaradar_churn is provided by the QA Radar MCP server (qaradar). 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 →