AI agents call retrieve_starlog 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 historical information from the starlog system without creating, modifying, or deleting data. The verb 'retrieve' and the term 'historical retrieval' clearly indicate a read-only operation. The selective nature implies filtering/querying capabilities, which are characteristic of Read operations. There is no indication of side effects, irreversible changes, code execution, or financial impact.
From the tool's definition Tool name contains 'retrieve' and description states 'Selective historical retrieval' — indicates querying or fetching existing data without modification.
Attacks that exploit this kind of access
Selective historical retrieval. 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 retrieve_starlog: 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.
retrieve_starlog 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 retrieve_starlog 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 retrieve_starlog. 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.
retrieve_starlog 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 →