search_planets
AI agents call search_planets to retrieve information from Nasa Exoplanet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves exoplanet data from a public NASA database with no side effects. While the description is empty, the name and context of sibling tools strongly indicate a read-only query function. The blast radius of misuse is minimal since it only accesses publicly available astronomical data without modification, deletion, or external side effects.
From the tool's definition Tool name 'search_planets' indicates a search operation that retrieves exoplanet data. Sibling tools like 'get_planet', 'list_columns', 'list_tables', and 'resolve_name' are all clearly read-only query operations on NASA's Exoplanet Archive database.
Attacks that exploit this kind of access
search_planets. It is categorised as a Read tool in the Nasa Exoplanet MCP Server, which means it retrieves data without modifying state.
Register the Nasa Exoplanet MCP server in PolicyLayer and add a rule for search_planets: 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 Exoplanet. Nothing to install.
search_planets 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 search_planets 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 search_planets. 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.
search_planets is provided by the Nasa Exoplanet MCP server (saikrmet/nasa-exoplanet-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 →