Add a folder as a
AI agents use add_room to create or update resources in Mnehmos Synch — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mnehmos Synch environment.
This tool creates new entities (folders/rooms) in the persistent context system, which is a reversible write operation. It modifies the organizational structure of the agent's memory store but does not execute arbitrary code, delete data, or move funds.
From the tool's definition Tool name 'add_room' and description 'Add a folder as a' indicate creation of a new organizational structure (room/folder) within the memory management system. The description is incomplete ('Add a folder as a' cuts off mid-sentence), which limits precision.
Attacks that exploit this kind of access
Add a folder as a. It is categorised as a Write tool in the Mnehmos Synch MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mnehmos Synch MCP server in PolicyLayer and add a rule for add_room: 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 Mnehmos Synch. Nothing to install.
add_room 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 add_room 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 add_room. 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.
add_room is provided by the Mnehmos Synch MCP server (mnehmos/mnehmos.synch.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 →