Run a multi-step workflow across Onyx tools in one paid call. Each step names a tool and its args; later steps can reference earlier outputs via {"$ref": "step_N.field"} or {"$prev": "field"}. Saves agents the round-trip + per-call gas of N separate x402 settles when they know the chain in advanc...
Part of the Onyx Mcp server.
Free to start. No card required.
AI agents invoke onyx_agent_workflow to trigger processes or run actions in Onyx Mcp. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
onyx_agent_workflow can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"onyx_agent_workflow": {
"limits": [
{
"counter": "onyx_agent_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Onyx Mcp policy for all 67 tools.
These attack patterns abuse exactly the kind of access onyx_agent_workflow gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run a multi-step workflow across Onyx tools in one paid call. Each step names a tool and its args; later steps can reference earlier outputs via {"$ref": "step_N.field"} or {"$prev": "field"}. Saves agents the round-trip + per-call gas of N separate x402 settles when they know the chain in advance — e.g. validate email → check domain DNS → solve captcha → submit form, all atomic. Stops on first step error and returns partial results. Cheaper than the unit-call sum because it bundles. (price: $0.020 USDC, tier: metered). It is categorised as a Execute tool in the Onyx Mcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Onyx MCP server in PolicyLayer and add a rule for onyx_agent_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 Onyx Mcp. Nothing to install.
onyx_agent_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 onyx_agent_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 onyx_agent_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.
onyx_agent_workflow is provided by the Onyx MCP server (https://onyx-actions.onrender.com/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 67 Onyx Mcp tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.