list_milestones_tool
AI agents call list_milestones_tool to retrieve information from MCP Gitlab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list' prefix in the tool name is a standard indicator of a retrieval operation. Listing milestones is a read-only query that retrieves existing data without modification, deletion, or execution of code. This aligns with the Read category. Severity is low as unauthorized access to milestone metadata poses minimal risk to system integrity.
From the tool's definition Tool name 'list_milestones_tool' indicates a listing operation that retrieves milestone data. No description provided, but the naming convention (list_*) and context within a GitLab MCP server strongly suggest a query operation with no side effects.
Attacks that exploit this kind of access
list_milestones_tool. It is categorised as a Read tool in the MCP Gitlab MCP Server, which means it retrieves data without modifying state.
Register the MCP Gitlab MCP server in PolicyLayer and add a rule for list_milestones_tool: 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 Gitlab. Nothing to install.
list_milestones_tool 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_tool 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_tool. 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_tool is provided by the MCP Gitlab MCP server (mcp-gitlab-crunchtools). 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 →