Take a snapshot of a time machine
AI agents use take_snapshot to create or update resources in NDB MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NDB MCP Server environment.
Taking a snapshot creates new data (a point-in-time backup copy) without deleting or overwriting existing data. This is a Write operation. Severity is medium because it consumes storage resources and could be misused to create many unnecessary snapshots, but it does not destroy or expose sensitive data.
From the tool's definition 'Take a snapshot of a time machine' — creates a new snapshot (point-in-time copy), which is a reversible write/create operation
Attacks that exploit this kind of access
Take a snapshot of a time machine. It is categorised as a Write tool in the NDB MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the NDB MCP Server MCP server in PolicyLayer and add a rule for take_snapshot: 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 NDB MCP Server. Nothing to install.
take_snapshot 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 take_snapshot 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 take_snapshot. 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.
take_snapshot is provided by the NDB MCP Server MCP server (rouxton/ndb-mcp-server). 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 →