Build a custom workflow with full control over phases and configuration. Use specific workflow tools (refactor_workflow, create_feature_workflow, etc.) for optimized presets.
AI agents invoke build_custom_workflow to trigger actions in Structured Workflow MCP. 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 enables execution of custom workflows with user-controlled phases and configuration. While it appears to be a workflow orchestration/control tool rather than a direct code execution tool, it still falls under Execute category because: (1) it triggers external operations (workflow execution) whose effects are determined by the arguments/configuration provided, (2) the 'full control over phases' suggests it…
From the tool's definition Tool description states 'Build a custom workflow with full control over phases and configuration', indicating it executes workflow operations and can trigger actions whose effects depend on how the workflow is configured.
Documented attack patterns abuse exactly the kind of access build_custom_workflow gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Structured Workflow MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for build_custom_workflow:
{
"version": "1",
"default": "deny",
"tools": {
"build_custom_workflow": {
"limits": [
{
"counter": "build_custom_workflow_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}build_custom_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.
Build a custom workflow with full control over phases and configuration. Use specific workflow tools (refactor_workflow, create_feature_workflow, etc.) for optimized presets. It is categorised as a Execute tool in the Structured Workflow MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Structured Workflow MCP server in PolicyLayer and add a rule for build_custom_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 Structured Workflow MCP. Nothing to install.
build_custom_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 build_custom_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 build_custom_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.
build_custom_workflow is provided by the Structured Workflow MCP server (kingdomseed/structured-workflow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Structured Workflow MCP, 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.
20 Structured Workflow MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.