AI agents call get_zodiac_by_date to retrieve information from Star MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation: it takes a birth date as input and returns the corresponding zodiac sign. It has no side effects, does not modify any data, and does not execute arbitrary code or operations. It is a pure read operation analogous to a database lookup query.
From the tool's definition Tool name 'get_zodiac_by_date' and description '根据出生日期确定星座' (determine zodiac by birth date) indicate a query operation that retrieves zodiac information based on input parameters. No modification, deletion, or execution of external code occurs.
Attacks that exploit this kind of access
根据出生日期确定星座. It is categorised as a Read tool in the Star MCP MCP Server, which means it retrieves data without modifying state.
Register the Star MCP server in PolicyLayer and add a rule for get_zodiac_by_date: 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 Star MCP. Nothing to install.
get_zodiac_by_date 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_zodiac_by_date 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_zodiac_by_date. 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_zodiac_by_date is provided by the Star MCP server (jlankellii/star-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 →