AI agents call list_milestones to retrieve information from Mcp Gmail 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 milestone data from a GitHub repository. It performs no modifications, deletions, or external operations—it only fetches information. The filtering options mentioned are query parameters that further refine the read operation without changing any state. Severity is low because unauthorized access to milestone metadata poses minimal risk compared to destructive or financial operations.
From the tool's definition Tool name 'list_milestones' and description 'List milestones in a GitHub repository' indicates a retrieval operation with no side effects. The verb 'list' is explicitly listed in the Read category definition.
Attacks that exploit this kind of access
List milestones in a GitHub repository with filtering options. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for list_milestones: 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 Gmail. Nothing to install.
list_milestones 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_milestones 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_milestones. 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_milestones is provided by the Mcp Gmail MCP server (@monsoft/mcp-gmail). 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 →