Use when you need to know which transits shape a period for a natal chart. Returns aggregate counts by body and aspect type. Call with mode="top" to also get the N strongest transits with enter/exact/leave-orb dates. Use mode="full" only when you genuinely need every transit (multi-MB payloads at...
Risk signalsHigh parameter count (18 properties) · Bulk/mass operation — affects multiple targets
Part of the Celestine server.
Free to start. No card required.
AI agents call transit_search to retrieve information from Celestine without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though transit_search only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"transit_search": {}
}
}See the full Celestine policy for all 12 tools.
These attack patterns abuse exactly the kind of access transit_search gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Use when you need to know which transits shape a period for a natal chart. Returns aggregate counts by body and aspect type. Call with mode="top" to also get the N strongest transits with enter/exact/leave-orb dates. Use mode="full" only when you genuinely need every transit (multi-MB payloads at ranges over a year — upstream may time out). Next step after mode="summary": pick interesting buckets from by_body / by_aspect, then re-call with mode="top" for narrative material.. It is categorised as a Read tool in the Celestine MCP Server, which means it retrieves data without modifying state.
Register the Celestine MCP server in PolicyLayer and add a rule for transit_search: 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 Celestine. Nothing to install.
transit_search 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 transit_search 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 transit_search. 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.
transit_search is provided by the Celestine MCP server (bouch/celestine). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 12 Celestine tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.