Dispatch a task to a specific node for background execution and retrieve results later. Creates a task file on the node, runs it in background, and provides a task ID for polling. Designed for A2A (agent-to-agent) workflows where one agent dispatches work and another retrieves results.
AI agents invoke omniwire_agent_task to trigger actions in OmniWire. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes tasks on remote infrastructure nodes in the background. The ability to dispatch arbitrary tasks to distributed nodes represents a significant Execute-category action. While it doesn't explicitly mention irreversible deletion (which would make it Destructive), the blast radius is high because a misused agent could run arbitrary commands across multiple nodes in the mesh.
From the tool's definition 'Dispatch a task to a specific node for background execution' and 'runs it in background' — executes commands/tasks on remote nodes; designed for A2A workflows where agents dispatch arbitrary work
Documented attack patterns abuse exactly the kind of access omniwire_agent_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OmniWire, and nothing reaches the server without passing your rules. This is the rule we recommend for omniwire_agent_task:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_agent_task": {
"limits": [
{
"counter": "omniwire_agent_task_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniwire_agent_task stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Dispatch a task to a specific node for background execution and retrieve results later. Creates a task file on the node, runs it in background, and provides a task ID for polling. Designed for A2A (agent-to-agent) workflows where one agent dispatches work and another retrieves results. It is categorised as a Execute tool in the OmniWire MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OmniWire MCP server in PolicyLayer and add a rule for omniwire_agent_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 OmniWire. Nothing to install.
omniwire_agent_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the omniwire_agent_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 omniwire_agent_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.
omniwire_agent_task is provided by the OmniWire MCP server (voidchecksum/omniwire). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OmniWire, 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.
88 OmniWire tools catalogued and risk-classified — across an index of 43,000+ MCP servers.