AI agents use session_append_turn to create or update resources in Atlas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Atlas environment.
The name implies adding data to an existing session record (a conversation turn), which is a reversible write operation. Given the context of an AI-powered FHIR clinical document server with session management, this likely appends a message or interaction to a session log. Empty description lowers confidence significantly.
From the tool's definition Tool name 'session_append_turn' suggests appending a turn to a session (conversation history), which is a write/create operation. Description is empty and uninformative.
Attacks that exploit this kind of access
session_append_turn. It is categorised as a Write tool in the Atlas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Atlas MCP server in PolicyLayer and add a rule for session_append_turn: 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.
session_append_turn 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 session_append_turn 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 session_append_turn. 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.
session_append_turn 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 →