wait_for_run_completion

THE RISK

High Risk

Why wait_for_run_completion needs a policy

This tool appears to coordinate execution of external workflows and tasks. While it is not itself destructive, it manages the lifecycle of Execute-category operations (run_deployed_task, run_uv_script_remote). Waiting for completion is part of the execution control flow and could be misused to hold resources or coordinate harmful multi-step operations.

From the tool's definition Tool name 'wait_for_run_completion' indicates it blocks/waits for a remote task execution to finish. In context of sibling tools like 'run_deployed_task' and 'run_uv_script_remote' that trigger external operations, this tool likely monitors and confirms…

Documented attack patterns abuse exactly the kind of access wait_for_run_completion gives an agent:

POLICY

How to control wait_for_run_completion

PolicyLayer is an MCP gateway — it sits between your AI agents and Union MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for wait_for_run_completion:

policy.json

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

wait_for_run_completion 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.

Create a free account and register Union MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Union MCP tools

Execute build_uv_script_image_remote build_uv_script_image_remote Execute run_deployed_task run_deployed_task Execute run_uv_script_remote run_uv_script_remote Read flyte_uv_script_example Get a full example of a Flyte script. Read flyte_uv_script_format Get the template format of a Flyte script. Read get_deployed_task Get a deployed task on the remote Flyte cluster. Read get_run Get run information. Read get_run_io Get inputs and outputs of a run.

All 14 Union MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Union MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about wait_for_run_completion

What does the wait_for_run_completion tool do? +

wait_for_run_completion. It is categorised as a Execute tool in the Union MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wait_for_run_completion? +

Register the Union MCP server in PolicyLayer and add a rule for wait_for_run_completion: 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 Union MCP. Nothing to install.

What risk level is wait_for_run_completion? +

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

Can I rate-limit wait_for_run_completion? +

Yes. Add a rate_limit block to the wait_for_run_completion 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 wait_for_run_completion completely? +

Set action: deny in the PolicyLayer policy for wait_for_run_completion. 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 wait_for_run_completion? +

wait_for_run_completion is provided by the Union MCP server (unionai-oss/union-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Union MCP tool call.

Start from Union MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →