List all active providers and registered tools.
AI agents call list_active_tools to retrieve information from Universal AI Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or enumerates system configuration data (active providers and registered tools). It is a read-only operation with no ability to modify, execute, delete, or interact with external systems. The blast radius is minimal—an agent discovering what tools are available poses negligible risk compared to actually invoking them.
From the tool's definition Tool name 'list_active_tools' and description 'List all active providers and registered tools' indicate a query operation that retrieves metadata about available tools and providers with no side effects.
Attacks that exploit this kind of access
List all active providers and registered tools. It is categorised as a Read tool in the Universal AI Hub MCP Server, which means it retrieves data without modifying state.
Register the Universal AI Hub MCP server in PolicyLayer and add a rule for list_active_tools: 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 Universal AI Hub. Nothing to install.
list_active_tools 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_active_tools 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_active_tools. 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_active_tools is provided by the Universal AI Hub MCP server (volkansah/universal-ai-hub). 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 →