search_instruments
AI agents call search_instruments to retrieve information from NASA PDS Registry MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches or queries the NASA PDS Registry for instrument information. Search operations are read-only with no side effects, data modifications, code execution, or destructive actions. The blast radius of misuse is minimal—an agent could perform repeated queries but cannot alter registry data or trigger external operations.
From the tool's definition Tool name 'search_instruments' with sibling tools 'search_collections', 'search_targets', 'search_investigations', 'search_instrument_hosts' all indicating read-only search operations.
Attacks that exploit this kind of access
search_instruments. It is categorised as a Read tool in the NASA PDS Registry MCP Server MCP Server, which means it retrieves data without modifying state.
Register the NASA PDS Registry MCP Server MCP server in PolicyLayer and add a rule for search_instruments: 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 PDS Registry MCP Server. Nothing to install.
search_instruments 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_instruments 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_instruments. 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_instruments is provided by the NASA PDS Registry MCP Server MCP server (nasa-pds/pds-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 →