get_cloud_records
Query the Adrata Cloud — the canonical, source-attributed, bitemporal record substrate — as one surface. Filter by entity, field, source, and classification, and read AS OF a point in time: as_of is when a fact was TRUE, as_of_recorded is what Adrata KNEW at that moment. Read-only and scoped to y...
This record as markdown: /tools/adrata-starfield-mcp/get-cloud-records.md
What get_cloud_records does on Starfield
AI agents call get_cloud_records to retrieve information from Starfield without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
as_of | string | — | RFC 3339 instant — valid time (defaults to now) |
limit | number | — | Rows per page (default 100, max 500) |
offset | number | — | |
entity_id | string | — | |
source_id | string | — | |
field_name | string | — | Machine name of the field |
entity_type | string | — | company | person | opportunity | pursuit | room | buyer_group | action | custom |
source_type | string | — | |
as_of_recorded | string | — | RFC 3339 instant — knowledge time (defaults to now) |
classification | string | — | public | internal | confidential | highly_confidential | restricted |
field_definition_id | string | — |
Parameters from the server's own tool schema.
Why get_cloud_records is rated Low
Even though get_cloud_records only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (11 properties)
Attacks that exploit this kind of access
The rule that runs get_cloud_records safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Starfield, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_cloud_records, this is the rule to start with:
get_cloud_records is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Starfield, apply this rule, and every get_cloud_records call is checked against it from then on.
Questions about get_cloud_records
Query the Adrata Cloud — the canonical, source-attributed, bitemporal record substrate — as one surface. Filter by entity, field, source, and classification, and read AS OF a point in time: as_of is when a fact was TRUE, as_of_recorded is what Adrata KNEW at that moment. Read-only and scoped to your workspace. Values are returned exactly as asserted, with their source and confidence; a missing confidence is null, never assumed. It is categorised as a Read tool in the Starfield MCP Server, which means it retrieves data without modifying state.
get_cloud_records accepts 11 parameters: as_of, limit, offset, entity_id, source_id, field_name, entity_type, source_type, as_of_recorded, classification, field_definition_id. The full parameter table on this page comes from the server's own tool schema.
Register the Starfield MCP server in PolicyLayer and add a rule for get_cloud_records: 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 Starfield. Nothing to install.
get_cloud_records 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 get_cloud_records 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 get_cloud_records. 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.
get_cloud_records is provided by the Starfield MCP server (@adrata/starfield-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Starfield, and thousands of servers like it.
This server
Across the catalogue