AI agents call get_compatibility 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 queries and returns compatibility information between zodiac signs. It performs a read-only lookup operation similar to sibling tools like get_daily_horoscope and get_zodiac_info. No data is created, modified, deleted, or financial/destructive actions occur. Misuse poses minimal risk—worst case is receiving irrelevant astrology data.
From the tool's definition Tool name 'get_compatibility' and description '获取两个星座的配对指数和关系分析' (retrieve compatibility index and relationship analysis between two star signs) indicate data retrieval with no modifications, deletions, or external side effects.
Attacks that exploit this kind of access
获取两个星座的配对指数和关系分析. 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_compatibility: 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_compatibility 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_compatibility 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_compatibility. 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_compatibility 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 →