Poll a command until a condition is met or timeout. Useful for waiting on deployments, services starting, builds completing. Returns when the assert pattern matches stdout.
AI agents invoke omniwire_watch 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 repeatedly runs commands on remote nodes (distributed infrastructure, SSH2 connection pooling), which constitutes remote code/command execution. The blast radius is high because it can execute arbitrary commands across multiple nodes in a mesh infrastructure, and misuse could trigger unintended operations or expose sensitive command outputs at scale.
From the tool's definition 'Poll a command until a condition is met or timeout' — the tool repeatedly executes arbitrary commands across distributed infrastructure nodes via SSH2 connections until a condition matches stdout.
Documented attack patterns abuse exactly the kind of access omniwire_watch 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_watch:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_watch": {
"limits": [
{
"counter": "omniwire_watch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniwire_watch 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.
Poll a command until a condition is met or timeout. Useful for waiting on deployments, services starting, builds completing. Returns when the assert pattern matches stdout. 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_watch: 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_watch 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_watch 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_watch. 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_watch 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.