AI agents use sandy_create_session to create or update resources in Sandy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sandy environment.
This tool creates a new session artifact (write operation) within the sandboxed environment. While it modifies the system state by instantiating a session resource, it is reversible (sessions can be terminated) and has no destructive or financial impact. The low severity reflects the confined sandbox context where credentials are not exposed and the operation is bounded.
From the tool's definition Creates a session and returns its scripts path—a state-creating operation that initializes a new sandboxed environment resource without destructive or irreversible effects.
Attacks that exploit this kind of access
Create a session and return its scripts path. It is categorised as a Write tool in the Sandy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sandy MCP server in PolicyLayer and add a rule for sandy_create_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 Sandy. Nothing to install.
sandy_create_session 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 sandy_create_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 sandy_create_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.
sandy_create_session is provided by the Sandy MCP server (jamestelfer/sandy). 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 →