Define and execute a named workflow (DAG of steps) that can be reused. Workflows are stored on disk and can be triggered by any agent. Supports conditional steps, fan-out/fan-in, and cross-node orchestration.
AI agents invoke omniwire_workflow 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 falls into Execute category because it runs arbitrary workflows (DAGs) that can trigger commands and operations across distributed infrastructure. The critical severity is justified because: (1) workflows can contain any steps and are reused across agents, (2) cross-node orchestration means a single misconfiguration or adversarial workflow could affect multiple nodes, (3) stored workflows can be triggered…
From the tool's definition Tool description states it can "Define and execute a named workflow (DAG of steps)" that "can be triggered by any agent" with "cross-node orchestration" capabilities.
Documented attack patterns abuse exactly the kind of access omniwire_workflow 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_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"omniwire_workflow": {
"limits": [
{
"counter": "omniwire_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}omniwire_workflow 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.
Define and execute a named workflow (DAG of steps) that can be reused. Workflows are stored on disk and can be triggered by any agent. Supports conditional steps, fan-out/fan-in, and cross-node orchestration. 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_workflow: 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_workflow 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_workflow 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_workflow. 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_workflow 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.