AI agents call list_most_recent_projects to retrieve information from Starlog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about recent projects for the user's reference. It has no side effects, does not modify state, and does not execute operations. The pagination feature is a standard read-operation parameter. Blast radius is minimal—incorrect usage simply returns no results or filtered results.
From the tool's definition Tool name 'list_most_recent_projects' and description 'List most recently used STARLOG projects with pagination' indicate data retrieval only. The verb 'list' is a read operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
List most recently used STARLOG projects with pagination. It is categorised as a Read tool in the Starlog MCP Server, which means it retrieves data without modifying state.
Register the Starlog MCP server in PolicyLayer and add a rule for list_most_recent_projects: 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 Starlog. Nothing to install.
list_most_recent_projects 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_most_recent_projects 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_most_recent_projects. 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_most_recent_projects is provided by the Starlog MCP server (sancovp/starlog-mcp). 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 →