Query async command status and output. taskId is returned by remote_exec_async.
AI agents call remote_task to retrieve information from Mcp Remote Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries and retrieves status/output data from already-executed async tasks. It has no side effects, does not create, modify, delete, or execute anything. The actual execution happens via remote_exec_async; this tool merely polls results. Classification: Read.
From the tool's definition Tool description states it 'Query async command status and output' — a read operation that retrieves results of previously executed commands without modifying state.
Attacks that exploit this kind of access
Query async command status and output. taskId is returned by remote_exec_async. It is categorised as a Read tool in the Mcp Remote Agent MCP Server, which means it retrieves data without modifying state.
Register the Mcp Remote Agent MCP server in PolicyLayer and add a rule for remote_task: 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 Remote Agent. Nothing to install.
remote_task 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 remote_task 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 remote_task. 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.
remote_task is provided by the Mcp Remote Agent MCP server (knownothing20/agentport). 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 →