Retrieve relevant observations for the current context. Use at the start of a session
AI agents call recall to retrieve information from Codewatch Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly retrieves stored observations from SQLite memory, consistent with a read/query operation. It is used at session start to fetch context, implying no modifications to data. No write, execute, or destructive behavior is described.
From the tool's definition "Retrieve relevant observations for the current context" - the tool retrieves/queries stored data with no side effects mentioned
Attacks that exploit this kind of access
Retrieve relevant observations for the current context. Use at the start of a session. It is categorised as a Read tool in the Codewatch Memory MCP Server, which means it retrieves data without modifying state.
Register the Codewatch Memory 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 Codewatch Memory. 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 Codewatch Memory MCP server (klausandrade/codewatch). 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 →