Get results from completed subagents
AI agents call get_subagent_results to retrieve information from MCP Goose Subagents Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries results from already-completed subagent executions. It performs no modifications, deletions, or triggering of new operations—it is purely a read operation. While the underlying subagent work may have executed code or other operations, this specific tool only reads their outcomes.
From the tool's definition Tool name 'get_subagent_results' and description 'Get results from completed subagents' indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Get results from completed subagents. It is categorised as a Read tool in the MCP Goose Subagents Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Goose Subagents Server MCP server in PolicyLayer and add a rule for get_subagent_results: 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 MCP Goose Subagents Server. Nothing to install.
get_subagent_results 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_subagent_results 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_subagent_results. 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_subagent_results is provided by the MCP Goose Subagents Server MCP server (lordstyled55/goose-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 →