AI agents call list_backends to retrieve information from Omni Fs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about registered file system backends, their configurations, and operational status. It performs no modifications, deletions, or external operations. However, the exposed configuration details (connection strings, credentials, authentication tokens) could be sensitive, warranting medium severity if an AI agent exfiltrates backend credentials to unauthorized parties.
From the tool's definition Tool name 'list_backends' and description 'List all registered backends with their configurations and status' indicate data retrieval with no side effects. The verb 'list' is explicitly listed in the Read category examples.
Attacks that exploit this kind of access
List all registered backends with their configurations and status. It is categorised as a Read tool in the Omni Fs MCP Server, which means it retrieves data without modifying state.
Register the Omni Fs MCP server in PolicyLayer and add a rule for list_backends: 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 Omni Fs. Nothing to install.
list_backends 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_backends 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_backends. 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_backends is provided by the Omni Fs MCP server (vaayne/omni-fs-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 →