AI agents use set_default_backend to create or update resources in Omni Fs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Omni Fs environment.
This tool creates or modifies configuration data reversibly (the default can be changed again), making it a Write operation rather than Read or Execute. It does not delete data (not Destructive), move money (not Financial), or directly execute arbitrary commands (not Execute).
From the tool's definition The tool modifies configuration state by setting a default backend preference. The description states 'Set the default backend for operations when no backend is specified,' which indicates it changes system configuration that affects subsequent operations.
Attacks that exploit this kind of access
Set the default backend for operations when no backend is specified. It is categorised as a Write tool in the Omni Fs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Omni Fs MCP server in PolicyLayer and add a rule for set_default_backend: 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.
set_default_backend 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_default_backend 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_default_backend. 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_default_backend 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 →