run_unified_workflow · DocAgent MCP: Risk & Policy

WHAT IT DOES

What run_unified_workflow does on DocAgent

AI agents invoke run_unified_workflow to trigger actions in DocAgent. 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.

WHY IT NEEDS A POLICY

Why run_unified_workflow needs a policy

This tool executes a sophisticated multi-component workflow (docagent + orchestrator) that produces side effects (documentation generation, file creation). While the outputs are reversible (documentation can be deleted), the tool itself performs computational operations and triggers external processes rather than merely retrieving data.

From the tool's definition Tool description states 'Run the unified workflow' which triggers automatic execution of complex LangGraph workflows that generate documentation artifacts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_unified_workflow Rate-limited

run_unified_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_unified_workflow": {
      "limits": [
        {
          "counter": "run_unified_workflow_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches DocAgent, so you can run agents against it safely.

FAQ

Questions about run_unified_workflow

What does the run_unified_workflow tool do? +

Run the unified workflow with both docagent and orchestrator working together automatically. It is categorised as a Execute tool in the DocAgent MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_unified_workflow? +

Register the DocAgent MCP server in PolicyLayer and add a rule for run_unified_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 DocAgent. Nothing to install.

What risk level is run_unified_workflow? +

run_unified_workflow is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_unified_workflow? +

Yes. Add a rate_limit block to the run_unified_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.

How do I block run_unified_workflow completely? +

Set action: deny in the PolicyLayer policy for run_unified_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.

What MCP server provides run_unified_workflow? +

run_unified_workflow is provided by the DocAgent MCP server (vinnyfds/docagent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.