AI agents call jpl_sentry 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 retrieves scientific data about near-earth objects and their potential impact risks. It has no capability to modify data, execute commands, delete information, or commit financial transactions. The worst case misuse would be an AI agent retrieving and presenting inaccurate risk assessments, but the underlying operation is purely informational read access to a public NASA database.
From the tool's definition Tool description states it provides 'NEO Earth impact risk assessment data' - this is a data retrieval operation that queries NASA's Sentry database for near-earth object information.
Attacks that exploit this kind of access
JPL Sentry - NEO Earth impact risk assessment data. 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_sentry: 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_sentry 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_sentry 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_sentry. 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_sentry 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 →