Capture streaming command output (for tail -f, watch, etc.) for a limited duration.
AI agents invoke omniwire_stream 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 streaming commands on remote infrastructure nodes (tail -f, watch, and similar). While described as 'capturing output,' it runs arbitrary commands across distributed nodes via SSH connections. The blast radius is high because an AI agent could misuse this to run malicious commands across the entire mesh infrastructure, not just observe output.
From the tool's definition Capture streaming command output (for tail -f, watch, etc.)
Documented attack patterns abuse exactly the kind of access omniwire_stream 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_stream:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_stream": {
"limits": [
{
"counter": "omniwire_stream_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniwire_stream 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.
Capture streaming command output (for tail -f, watch, etc.) for a limited duration. 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_stream: 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_stream 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_stream 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_stream. 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_stream 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.