Remember a memory for future context
AI agents use squish_remember to create or update resources in Squish Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Squish Memory environment.
This tool writes (stores) information to a shared memory store that persists across sessions and AI agents. It creates new data reversibly (memories could presumably be deleted), so it falls under Write. The blast radius is medium because a misbehaving agent could pollute shared memory with false or misleading context that affects all downstream AI interactions across tools.
From the tool's definition 'Remember a memory for future context' — creates/stores new data persistently in a shared memory system
Attacks that exploit this kind of access
Remember a memory for future context. It is categorised as a Write tool in the Squish Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Squish Memory MCP server in PolicyLayer and add a rule for squish_remember: 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_remember is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the squish_remember 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_remember. 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_remember 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 →