記録候補をdraftとして保存(承認前の仮保存)
AI agents use memory_save_draft to create or update resources in MCP Memory System — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Memory System environment.
This tool creates or modifies data (draft memory records) in a reversible manner—drafts can be discarded, edited, or superseded without permanent consequences. It does not execute code, delete data irreversibly, move money, or retrieve data (though retrieval is incidental). The 'draft' status and pre-approval nature confirm the action is not destructive.
From the tool's definition Tool name 'memory_save_draft' and description indicating it saves record candidates as drafts (仮保存) before approval, indicating reversible creation/modification of data in draft state.
Attacks that exploit this kind of access
記録候補をdraftとして保存(承認前の仮保存). It is categorised as a Write tool in the MCP Memory System MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Memory System MCP server in PolicyLayer and add a rule for memory_save_draft: 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 MCP Memory System. Nothing to install.
memory_save_draft 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_save_draft 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_save_draft. 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_save_draft is provided by the MCP Memory System MCP server (workerportfolio/mcp-memory-system). 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 →