AI agents call get_bucket_policy to retrieve information from Rustfs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the access control policy of an S3 bucket, which is a query operation that returns information without side effects. Reading bucket policies poses minimal risk—no data is modified, deleted, or destroyed. The worst case is information disclosure of policy rules already set by the bucket owner, which is typically intended to be readable by authorized administrators.
From the tool's definition Tool name 'get_bucket_policy' and description 'Get the bucket policy JSON' indicate a retrieval operation with no modification of data or state. The verb 'Get' confirms read-only semantics.
Attacks that exploit this kind of access
Get the bucket policy JSON (null if none is set). It is categorised as a Read tool in the Rustfs MCP Server, which means it retrieves data without modifying state.
Register the Rustfs MCP server in PolicyLayer and add a rule for get_bucket_policy: 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 Rustfs. Nothing to install.
get_bucket_policy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_bucket_policy 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 get_bucket_policy. 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.
get_bucket_policy is provided by the Rustfs MCP server (stackblaze/rustfs-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 →