Near-Earth asteroid/comet close approaches to Earth in a date window + max distance (NASA JPL CAD). Returns designation, date, distance (AU + lunar distances), relative velocity, magnitude. Sorted nearest-first.
AI agents call space.close-approaches to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries NASA JPL's Close Approach Data (CAD) and returns read-only astronomical data. No side effects, no data modification, no execution of commands. It simply retrieves and returns observational data about near-Earth objects. Severity is low as misuse would at most return irrelevant or excessive query results, with no financial, destructive, or operational impact.
From the tool's definition 'Near-Earth asteroid/comet close approaches to Earth in a date window + max distance (NASA JPL CAD). Returns designation, date, distance (AU + lunar distances), relative velocity, magnitude. Sorted nearest-first.'
Attacks that exploit this kind of access
Near-Earth asteroid/comet close approaches to Earth in a date window + max distance (NASA JPL CAD). Returns designation, date, distance (AU + lunar distances), relative velocity, magnitude. Sorted nearest-first. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for space.close-approaches: 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 Mcp. Nothing to install.
space.close-approaches 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 space.close-approaches 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 space.close-approaches. 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.
space.close-approaches is provided by the MCP server (@2sio/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 →