Unified search interface for astronomical objects. Currently supports DESI via Data Lab SQL queries. Supports coordinate-based searches (point/cone/box), object type filtering, redshift constraints, and DESI tracer filtering (LRG, ELG, BGS, QSO). Automatically saves results with descriptive filen...
AI agents call search_objects to retrieve information from Astro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries astronomical data from DESI and related databases without creating, modifying, or deleting any data. It performs read-only operations: coordinate searches, filtering, and result caching.
From the tool's definition Tool description explicitly states it is a 'search interface' that 'supports coordinate-based searches', 'object type filtering', and 'redshift constraints'.
Attacks that exploit this kind of access
Unified search interface for astronomical objects. Currently supports DESI via Data Lab SQL queries. Supports coordinate-based searches (point/cone/box), object type filtering, redshift constraints, and DESI tracer filtering (LRG, ELG, BGS, QSO). Automatically saves results with descriptive filenames. It is categorised as a Read tool in the Astro MCP MCP Server, which means it retrieves data without modifying state.
Register the Astro MCP server in PolicyLayer and add a rule for search_objects: 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 Astro MCP. Nothing to install.
search_objects 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_objects 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_objects. 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_objects is provided by the Astro MCP server (sandyyuan/astro_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_objects is one line of Astro's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →