AI agents call sst_get_events to retrieve information from MCP-SST without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical event data from a development event stream. It is purely informational—reading events does not trigger deployments, execute code, modify infrastructure, or cause irreversible changes. The worst-case misuse would be information disclosure about the development process, which is low risk in a development environment context.
From the tool's definition Tool name 'sst_get_events' and description 'Get recent events from the SST dev event stream' indicate a retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Get recent events from the SST dev event stream. It is categorised as a Read tool in the MCP-SST MCP Server, which means it retrieves data without modifying state.
Register the MCP-SST MCP server in PolicyLayer and add a rule for sst_get_events: 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 MCP-SST. Nothing to install.
sst_get_events 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 sst_get_events 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 sst_get_events. 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.
sst_get_events is provided by the MCP-SST MCP server (shanewwarren/mcp-sst). 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 →