AI agents call list_capabilities to retrieve information from Red-team-mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure information retrieval tool that enumerates available features. While it exists in a red-team context, the tool itself performs no execution, modification, or destruction.
From the tool's definition The tool name 'list_capabilities' and description 'List all available red team capabilities' indicate a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access list_capabilities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Red-team-mcp, and nothing reaches the server without passing your rules. This is the rule we recommend for list_capabilities:
{
"version": "1",
"default": "deny",
"tools": {
"list_capabilities": {}
}
}list_capabilities is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all available red team capabilities. It is categorised as a Read tool in the Red-team-mcp MCP Server, which means it retrieves data without modifying state.
Register the Red-team- MCP server in PolicyLayer and add a rule for list_capabilities: 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 Red-team-mcp. Nothing to install.
list_capabilities 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_capabilities 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_capabilities. 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_capabilities is provided by the Red-team- MCP server (skjortan23/read-team-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Red-team-mcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Red-team-mcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.