AI agents call list_regressions to retrieve information from Pulspeed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves performance regression data from past scans—it does not modify, delete, execute code, or trigger financial transactions. It is purely informational, analyzing consecutive scan results to display degradation trends. The low severity reflects minimal blast radius: misuse would only expose or display performance data that already exists.
From the tool's definition Tool name 'list_regressions' and description 'Show recent performance regressions' indicates retrieval and querying of historical performance data.
Attacks that exploit this kind of access
Show recent performance regressions for a site: consecutive scans where the performance score dropped significantly. Helps identify when and by how much the site degraded. It is categorised as a Read tool in the Pulspeed MCP Server, which means it retrieves data without modifying state.
Register the Pulspeed MCP server in PolicyLayer and add a rule for list_regressions: 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 Pulspeed. Nothing to install.
list_regressions 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 list_regressions 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 list_regressions. 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.
list_regressions is provided by the Pulspeed MCP server (pulspeed/mcp-server). 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 →