recall
Search saved memories by text query. Returns memories ranked by relevance. Use this to recall facts, preferences, deal context, or patterns from previous conversations.
This record as markdown: /tools/adrata-starfield-mcp/recall.md
What recall does on Starfield
AI agents call recall 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 |
|---|---|---|---|
limit | number | — | Max results (default 10, max 50) |
query | string | Yes | Search query (e.g. "competitors in payments", "user preferences") |
memory_type | string | — | Filter by memory type |
Parameters from the server's own tool schema.
Why recall is rated Low
Even though recall 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.
Attacks that exploit this kind of access
The rule that runs recall 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 recall, this is the rule to start with:
recall 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 recall call is checked against it from then on.
Questions about recall
Search saved memories by text query. Returns memories ranked by relevance. Use this to recall facts, preferences, deal context, or patterns from previous conversations. It is categorised as a Read tool in the Starfield MCP Server, which means it retrieves data without modifying state.
recall accepts 3 parameters: limit, query, memory_type. Required: query. 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 recall: 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.
recall 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 recall 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 recall. 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.
recall 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