System introspection - discover available capabilities, connected servers, and tool inventory. Use this to understand what the orchestrator can do before making complex requests.
AI agents call get_info to retrieve information from Orchestrator MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about the system's capabilities and connected servers. It performs read-only system introspection with no capacity to modify, delete, execute code, or trigger external operations. The discovery of available tools and capabilities is foundational system metadata retrieval, making it a low-severity Read operation.
From the tool's definition Tool name is 'get_info' and description states it 'discover[s] available capabilities, connected servers, and tool inventory' — a retrieval and introspection operation with no side effects.
Documented attack patterns abuse exactly the kind of access get_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Orchestrator MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_info:
{
"version": "1",
"default": "deny",
"tools": {
"get_info": {}
}
}get_info 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.
System introspection - discover available capabilities, connected servers, and tool inventory. Use this to understand what the orchestrator can do before making complex requests. It is categorised as a Read tool in the Orchestrator MCP MCP Server, which means it retrieves data without modifying state.
Register the Orchestrator MCP server in PolicyLayer and add a rule for get_info: 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 Orchestrator MCP. Nothing to install.
get_info 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 get_info 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 get_info. 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.
get_info is provided by the Orchestrator MCP server (phoenixrr2113/orchestrator-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Orchestrator 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.
3 Orchestrator MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.