Switch to a different room
AI agents use switch_kogna_room to create or update resources in Kogna MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kogna MCP Server environment.
This tool changes the active conversation room, which is a reversible state modification. It does not retrieve data (Read), execute arbitrary code (Execute), delete anything (Destructive), or move money (Financial). While the change is persistent across a session, switching rooms is a normal conversation navigation action that can be undone by switching back.
From the tool's definition Tool name: 'switch_kogna_room' with description 'Switch to a different room'. This modifies the user's conversation context/state by changing their active room.
Attacks that exploit this kind of access
Switch to a different room. It is categorised as a Write tool in the Kogna MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kogna MCP Server MCP server in PolicyLayer and add a rule for switch_kogna_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 Kogna MCP Server. Nothing to install.
switch_kogna_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 switch_kogna_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 switch_kogna_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.
switch_kogna_room is provided by the Kogna MCP Server MCP server (subbu3012/kognamcp). 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 →