AI agents call security_alerts to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays existing security alert information from GitHub's Dependabot and code scanning features. It has no side effects, does not modify data, and does not trigger actions. It is purely informational—a read operation used to view the state of security findings.
From the tool's definition Tool name 'security_alerts' combined with description 'List security alerts (Dependabot, code scanning)' indicates a retrieval operation. The verb 'List' explicitly describes querying/reading alert data without modification.
Attacks that exploit this kind of access
List security alerts (Dependabot, code scanning). It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.
Register the Git Steer MCP server in PolicyLayer and add a rule for security_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 Git Steer. Nothing to install.
security_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 security_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 security_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.
security_alerts is provided by the Git Steer MCP server (ry-ops/git-steer). 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 →