Clear agent session history for a given session ID.
AI agents call agent_clear_session to permanently remove resources in Atlas — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes session history data. While the blast radius is limited to a single session's history (not clinical FHIR documents themselves), this action cannot be undone, making it Destructive. Severity is medium because it affects only conversation/session metadata rather than primary clinical data.
From the tool's definition 'Clear agent session history' — clearing session history is an irreversible deletion of stored conversation/session data for a given session ID.
Attacks that exploit this kind of access
Clear agent session history for a given session ID. It is categorised as a Destructive tool in the Atlas MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Atlas MCP server in PolicyLayer and add a rule for agent_clear_session: 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 Atlas. Nothing to install.
agent_clear_session is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the agent_clear_session 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 agent_clear_session. 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.
agent_clear_session is provided by the Atlas MCP server (rsanandres/atlas_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 →