AI agents call starlog_guide 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 reads and returns instructional content about the STARLOG system. It has no capacity to modify, delete, execute code, or create financial obligations. The action is a simple informational query with no state changes or external effects, making it clearly a Read operation with low severity.
From the tool's definition Tool name 'starlog_guide' and description 'Returns STARLOG system workflow and tool usage guide' indicate it retrieves and displays documentation/guidance information with no side effects.
Attacks that exploit this kind of access
Returns STARLOG system workflow and tool usage guide. 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 starlog_guide: 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.
starlog_guide 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 starlog_guide 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 starlog_guide. 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.
starlog_guide 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 →