AI agents call get_milestone 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.
The tool retrieves milestone metadata from a GitHub repository. The verb 'get' and the passive framing ('get details') confirm this is a read-only query operation. No data is created, modified, deleted, or executed. The low severity reflects that accessing milestone information poses minimal risk—it only exposes metadata that is typically not sensitive.
From the tool's definition Tool name 'get_milestone' and description 'Get details of a specific milestone' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get details of a specific milestone in a GitHub repository. 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 get_milestone: 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.
get_milestone 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 get_milestone 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 get_milestone. 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.
get_milestone 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 →