Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash...
AI agents call recall to retrieve information from Expression Atlas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
key | string | — | Memory key to retrieve (omit to list all keys) |
Parameters from the server's own tool schema.
The tool only reads/retrieves previously stored values or lists keys. It has no side effects and cannot modify or delete data. Scoped to the user's identifier, limiting blast radius to that user's stored context only.
From the tool's definition Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier
Attacks that exploit this kind of access
Retrieve a value previously saved via remember, or list all saved keys (omit the key argument). Use to look up context the agent stored earlier — the user's target ticker, an address, prior research notes — without re-deriving it from scratch. Scoped to your identifier (anonymous IP, BYO key hash, or account ID). Pair with remember to save, forget to delete. It is categorised as a Read tool in the Expression Atlas MCP Server, which means it retrieves data without modifying state.
recall accepts 1 parameter: key. The full parameter table on this page comes from the server's own tool schema.
Register the Expression Atlas 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 Expression Atlas. 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 Expression Atlas MCP server (https://gateway.pipeworx.io/expression-atlas/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 →