List all available capabilities and agent types including advanced upgrades
AI agents call list_capabilities to retrieve information from Multi Agent Orchestrator MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation. It queries and returns information about available capabilities and agent types. There are no side effects, no code execution, no data modification, and no destructive actions. The tool simply enumerates capabilities for visibility/documentation purposes, making it low severity with high confidence.
From the tool's definition Tool name is 'list_capabilities' and description states it 'List all available capabilities and agent types' — a straightforward query operation that retrieves and displays information without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all available capabilities and agent types including advanced upgrades. It is categorised as a Read tool in the Multi Agent Orchestrator MCP MCP Server, which means it retrieves data without modifying state.
Register the Multi Agent Orchestrator 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 Multi Agent Orchestrator 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 Multi Agent Orchestrator MCP server (ssdeanx/orchestrator-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 →