AI agents use add_deny_path to create or update resources in Unlimited — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unlimited environment.
This tool creates or modifies configuration data (deny_paths list) that controls system access policies. It is reversible (paths can presumably be removed), so it is Write rather than Destructive. However, severity is high because misconfiguring deny paths could inadvertently block critical system resources or security-sensitive paths, or conversely, fail to block paths that should be denied.
From the tool's definition Tool name is 'add_deny_path' and description states it 'Add[s] a path to deny_paths (always blocked, even if inside an allowed root)'. This modifies a deny list configuration, creating or adding to a security policy list.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Add a path to deny_paths (always blocked, even if inside an allowed root). It is categorised as a Write tool in the Unlimited MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Unlimited MCP server in PolicyLayer and add a rule for add_deny_path: 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 Unlimited. Nothing to install.
add_deny_path 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_deny_path 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_deny_path. 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_deny_path is provided by the Unlimited MCP server (triumsebas/unlimited-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 →