Save a new technique to the memory library with stylistic qualities. type must be one of: beat_pattern, device_chain, mix_template, browser_pin, preference. qualities must include at minimum a 'summary' field.
AI agents use memory_learn to create or update resources in Livepilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Livepilot environment.
An AI agent can call memory_learn faster than any human can review — one bad instruction and it creates or modifies resources in Livepilot by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Save a new technique to the memory library with stylistic qualities. type must be one of: beat_pattern, device_chain, mix_template, browser_pin, preference. qualities must include at minimum a 'summary' field. It is categorised as a Write tool in the Livepilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Livepilot MCP server in PolicyLayer and add a rule for memory_learn: 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 Livepilot. Nothing to install.
memory_learn 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 memory_learn 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 memory_learn. 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.
memory_learn is provided by the Livepilot MCP server (livepilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.