AI agents call list_orphans to retrieve information from Llauncher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about processes—specifically orphaned llama-server instances not tracked by the management system. It performs no side effects, does not create, modify, delete, or execute anything; it only reads and reports state. This is a classic Read operation.
From the tool's definition Tool name 'list_orphans' and description 'List unmanaged llama-server processes on this node' indicate a query/retrieval operation that enumerates existing processes without modification.
Attacks that exploit this kind of access
List unmanaged llama-server processes on this node. It is categorised as a Read tool in the Llauncher MCP Server, which means it retrieves data without modifying state.
Register the Llauncher MCP server in PolicyLayer and add a rule for list_orphans: 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 Llauncher. Nothing to install.
list_orphans 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_orphans 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_orphans. 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_orphans is provided by the Llauncher MCP server (shanevcantwell/llauncher). 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 →