AI agents use tigris_create_bucket to create or update resources in Tigris — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tigris environment.
This tool creates a new bucket (cloud storage container) in the user's Tigris account. This is a reversible Write operation—buckets can be deleted. The severity is medium because creating buckets consumes account resources and quota, and an AI agent could potentially exhaust storage limits or create many unused buckets, but the action is not destructive (the bucket can be removed) and does not involve financial…
From the tool's definition Tool name 'tigris_create_bucket' and description 'Create a Tigris bucket in your account' indicate creation of a new resource.
Attacks that exploit this kind of access
Create a Tigris bucket in your account. It is categorised as a Write tool in the Tigris MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tigris MCP server in PolicyLayer and add a rule for tigris_create_bucket: 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 Tigris. Nothing to install.
tigris_create_bucket 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 tigris_create_bucket 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 tigris_create_bucket. 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.
tigris_create_bucket is provided by the Tigris MCP server (@tigrisdata/tigris-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 →