AI agents use memo_save to create or update resources in Llama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Llama environment.
The tool creates or modifies deal-related content through manual HTML input. This is a Write operation because it stores new or updated information reversibly. Severity is medium because while it modifies deal data, it appears scoped to memo/override content rather than destructive actions.
From the tool's definition Tool name 'memo_save' combined with description 'Save hand-written HTML as a manual override for a deal' indicates creation or modification of data (a memo/override associated with a deal).
Attacks that exploit this kind of access
Save hand-written HTML as a manual override for a deal. It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Llama MCP server in PolicyLayer and add a rule for memo_save: 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 Llama. Nothing to install.
memo_save 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 memo_save 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 memo_save. 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.
memo_save is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →