AI agents invoke run_workflow to trigger actions in RAD Security. 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 workflows—automated processes whose side effects depend on the provided arguments. Although the specific impacts depend on what these workflows do (scanning vs. remediation), the core function of triggering and running automated operations with configurable parameters places it firmly in the Execute category.
From the tool's definition "Run a workflow" indicates execution of pre-defined automated processes. The phrase "with optional argument overrides" demonstrates that execution effects are argument-dependent, which is the key Execute criterion.
Documented attack patterns abuse exactly the kind of access run_workflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and RAD Security, and nothing reaches the server without passing your rules. This is the rule we recommend for run_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"run_workflow": {
"limits": [
{
"counter": "run_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_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.
Run a workflow with optional argument overrides. It is categorised as a Execute tool in the RAD Security MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the RAD Security MCP server in PolicyLayer and add a rule for run_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 RAD Security. Nothing to install.
run_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 run_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 run_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.
run_workflow is provided by the RAD Security MCP server (rad-security/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from RAD Security, 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.
55 RAD Security tools catalogued and risk-classified — across an index of 43,000+ MCP servers.