List the current GitHub Dependabot alerts for a repository
AI agents call list_dependabot_alerts to retrieve information from GHAS MCP server (GitHub Advanced Security) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing security alert data from GitHub without creating, modifying, deleting, or executing any operations. It is a passive data retrieval mechanism that has no side effects on the repository or system state.
From the tool's definition Tool name contains 'list' and description states 'List the current GitHub Dependabot alerts for a repository' — a retrieval operation with no modification capability.
Attacks that exploit this kind of access
List the current GitHub Dependabot alerts for a repository. It is categorised as a Read tool in the GHAS MCP server (GitHub Advanced Security) MCP Server, which means it retrieves data without modifying state.
Register the GHAS MCP server (GitHub Advanced Security) MCP server in PolicyLayer and add a rule for list_dependabot_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 GHAS MCP server (GitHub Advanced Security). Nothing to install.
list_dependabot_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 list_dependabot_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 list_dependabot_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.
list_dependabot_alerts is provided by the GHAS MCP server (GitHub Advanced Security) MCP server (rajbos/ghas-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 →