AI agents call sigsci_list_alerts to retrieve information from Sigsci without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves alert data from the Signal Sciences API without performing any write, delete, execute, or financial operations. The blast radius of misuse is low—an attacker could enumerate alerts but cannot modify security configurations, trigger actions, or access sensitive credential data beyond what alerts themselves may contain.
From the tool's definition Tool name 'sigsci_list_alerts' and description 'List all alerts for a site' indicate data retrieval with no modification capabilities. Confirmed by server description stating '40+ read-only tools'. The 'list' operation is a standard query operation.
Attacks that exploit this kind of access
List all alerts for a site. It is categorised as a Read tool in the Sigsci MCP Server, which means it retrieves data without modifying state.
Register the Sigsci MCP server in PolicyLayer and add a rule for sigsci_list_alerts: 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 Sigsci. Nothing to install.
sigsci_list_alerts 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 sigsci_list_alerts 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 sigsci_list_alerts. 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.
sigsci_list_alerts is provided by the Sigsci MCP server (yuki777/sigsci-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 →