AI agents call recall_code to retrieve information from Memex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or query stored code from the memory system without modifying, executing, or deleting anything. It fits the Read category as a recall/fetch operation. Severity is low because querying memory poses minimal risk—no side effects, no external operations triggered, no data destruction.
From the tool's definition Tool name 'recall_code' suggests retrieval/querying of code from the centralized memory system. The server description emphasizes 'persistent memory recall' as a core function, and the tool follows a pattern consistent with read operations (cf.
Attacks that exploit this kind of access
recall_code. It is categorised as a Read tool in the Memex MCP Server, which means it retrieves data without modifying state.
Register the Memex MCP server in PolicyLayer and add a rule for recall_code: 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 Memex. Nothing to install.
recall_code 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_code 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_code. 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_code is provided by the Memex MCP server (queflyhq/memex). 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 →