AI agents call jpl_cad to retrieve information from Nasa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries NASA's JPL Close Approach Data (CAD) system to retrieve historical and predictive astronomical data about celestial objects. It is purely informational with no side effects, no code execution, no data modification, and no financial implications. The severity is low because misuse would only return irrelevant or excessive data queries without harming systems or data integrity.
From the tool's definition Tool name 'jpl_cad' and description state it retrieves 'Asteroid and comet close approaches to the planets in the past and future' — a query/lookup operation with no data modification or external effects.
Attacks that exploit this kind of access
Asteroid and comet close approaches to the planets in the past and future. It is categorised as a Read tool in the Nasa MCP Server, which means it retrieves data without modifying state.
Register the Nasa MCP server in PolicyLayer and add a rule for jpl_cad: 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 Nasa. Nothing to install.
jpl_cad 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 jpl_cad 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 jpl_cad. 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.
jpl_cad is provided by the Nasa MCP server (@programcomputer/nasa-mcp-server). 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 →