Fetch recent Conjunction Data Messages (CDMs) from Space-Track.
AI agents call conjunction_query to retrieve information from Spacetrack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves publicly available satellite conjunction data from the NASA Space-Track API. It performs a read-only query operation with no side effects, no data modification, and no destructive capabilities. The 'fetch' operation is a standard information retrieval action.
From the tool's definition Tool description states 'Fetch recent Conjunction Data Messages (CDMs)' - the verb 'fetch' indicates data retrieval with no modification or deletion capability.
Attacks that exploit this kind of access
Fetch recent Conjunction Data Messages (CDMs) from Space-Track. It is categorised as a Read tool in the Spacetrack MCP Server, which means it retrieves data without modifying state.
Register the Spacetrack MCP server in PolicyLayer and add a rule for conjunction_query: 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 Spacetrack. Nothing to install.
conjunction_query 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 conjunction_query 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 conjunction_query. 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.
conjunction_query is provided by the Spacetrack MCP server (kaushik701/spacetrack-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 →