AI agents use add_access_key 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.
The tool creates new access keys (service accounts) for S3-compatible storage, which is a reversible write operation that modifies security infrastructure. While credential creation is sensitive and could enable unauthorized access if misused by an AI agent, it is not destructive (the key can be deleted via delete_access_key) nor financial.
From the tool's definition Tool description states 'Create a scoped access key (service account) for a user', indicating irreversible creation of authentication credentials.
Attacks that exploit this kind of access
Create a scoped access key (service account) for a user. (Refused read-only.). 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 add_access_key: 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.
add_access_key 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 add_access_key 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 add_access_key. 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.
add_access_key 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 →