创建 TOS 存储桶
AI agents use tos_create_bucket to create or update resources in TOS MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TOS MCP Server environment.
Creating a bucket is a write operation that establishes new cloud storage infrastructure. While reversible (buckets can be deleted), this action has significant blast radius in a production environment—an AI agent could create numerous buckets, consume quota, incur costs, or interfere with legitimate infrastructure.
From the tool's definition Tool name 'tos_create_bucket' and description '创建 TOS 存储桶' (Create TOS bucket) indicate creation of cloud storage infrastructure. This is a reversible data/resource creation operation typical of Write category.
Attacks that exploit this kind of access
创建 TOS 存储桶. It is categorised as a Write tool in the TOS MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the TOS MCP Server MCP server in PolicyLayer and add a rule for tos_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 TOS MCP Server. Nothing to install.
tos_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 tos_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 tos_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.
tos_create_bucket is provided by the TOS MCP Server MCP server (jneless/tos-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 →