AI agents call list_access_keys 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 and enumerates existing access keys, which is a read-only operation. However, the severity is elevated from 'low' to 'medium' because access keys are sensitive authentication credentials—exposing their list could enable an attacker to identify valid key IDs for further exploitation (e.g., via social engineering or targeting). The blast radius depends on what information is returned (IDs only vs.
From the tool's definition Tool name 'list_access_keys' and description 'List service-account access keys for a user' indicate a retrieval/query operation with no data modification.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
List service-account access keys for a user (defaults to the root user). 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 list_access_keys: 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.
list_access_keys 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 list_access_keys 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 list_access_keys. 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.
list_access_keys 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 →