New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

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...

SERVERStarfield SOURCE@adrata/starfield-mcp
Low RISK CLASS
Category Read
Parameters 110 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

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.

ParameterTypeRequiredDescription
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)

Questions about get_cloud_records

What does the get_cloud_records tool do? +

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.

What parameters does get_cloud_records accept? +

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.

How do I enforce a policy on get_cloud_records? +

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.

What risk level is get_cloud_records? +

get_cloud_records is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_cloud_records? +

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.

How do I block get_cloud_records completely? +

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.

What MCP server provides get_cloud_records? +

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.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Starfield's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.