Recall memories by search query
AI agents call squish_recall to retrieve information from Squish Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries stored memories and returns results based on a search parameter. It performs a read-only operation that retrieves data without creating, modifying, deleting, or executing anything. The action is purely informational with minimal risk if misused—an AI agent could retrieve memories but cannot alter, destroy, or financially impact the system.
From the tool's definition Tool name 'squish_recall' and description 'Recall memories by search query' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Recall memories by search query. It is categorised as a Read tool in the Squish Memory MCP Server, which means it retrieves data without modifying state.
Register the Squish Memory MCP server in PolicyLayer and add a rule for squish_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 Squish Memory. Nothing to install.
squish_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 squish_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 squish_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.
squish_recall is provided by the Squish Memory MCP server (michielhdoteth/squish). 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 →