Inject memory context into current session
AI agents call squish_context 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 retrieves and provides memory context that was previously stored (by squish_remember or similar write tools) and makes it available to the current session. It does not create, modify, delete, or execute anything—it only reads and delivers stored information. The action is non-destructive and has no side effects beyond making data visible to the AI agent.
From the tool's definition Tool name 'squish_context' and description 'Inject memory context into current session' indicates retrieval and injection of previously stored memory data into the current conversation.
Attacks that exploit this kind of access
Inject memory context into current session. 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_context: 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_context 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_context 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_context. 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_context 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 →