AI agents use update_memo to create or update resources in Memos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Memos environment.
This tool creates or modifies data (a memo) in a reversible manner without deleting or destroying anything. It does not execute arbitrary code or commit financial transactions. Write category is appropriate. Severity is medium because an agent could inadvertently overwrite important memo content, but the change is reversible (assuming version history or undo exists in the Memos service).
From the tool's definition Tool name is 'update_memo' and the description translates to 'Update memo/notes'. The server description confirms this server 'write[s]...and manage memos'. Update operations modify data reversibly.
Attacks that exploit this kind of access
更新备忘录. It is categorised as a Write tool in the Memos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Memos MCP server in PolicyLayer and add a rule for update_memo: 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 Memos. Nothing to install.
update_memo 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 update_memo 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 update_memo. 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.
update_memo is provided by the Memos MCP server (yuzhi-jiang/memos-mcp). 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 →