AI agents use switch_profile to create or update resources in Ogham — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ogham environment.
This is a Write operation because it changes the system's active configuration/state (selecting a different memory profile) without deleting data. The severity is medium because switching profiles could redirect subsequent read/write operations to different data sets, potentially causing confusion or misrouting of agent actions, but the action itself is reversible (switch back to previous profile).
From the tool's definition The tool 'switch_profile' modifies state by changing the active memory profile, similar to switching contexts or configurations. The description likens it to 'Severance', suggesting it separates or switches between distinct memory states.
Attacks that exploit this kind of access
Switch to a different memory profile. Like Severance -- each profile is. It is categorised as a Write tool in the Ogham MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ogham MCP server in PolicyLayer and add a rule for switch_profile: 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 Ogham. Nothing to install.
switch_profile 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_profile 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_profile. 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_profile is provided by the Ogham MCP server (ogham-mcp/ogham-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 →