AI agents use set_bucket_policy to create or update resources in Rustfs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rustfs environment.
Setting bucket policies modifies S3 access control rules and permissions, which can grant or revoke access to sensitive data. This is a Write operation because policy changes are reversible (can be updated or deleted), but the blast radius is high because misconfigured policies could expose or lock down entire buckets, affecting data availability and security posture.
From the tool's definition Tool name 'set_bucket_policy' and description 'Set a bucket policy (JSON string)' indicate modification of bucket access control policies, a reversible configuration change.
Attacks that exploit this kind of access
Set a bucket policy (JSON string). (Refused on read-only / production add-ons.). It is categorised as a Write tool in the Rustfs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rustfs MCP server in PolicyLayer and add a rule for set_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.
set_bucket_policy 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 set_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 set_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.
set_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 →