run_deployed_task
AI agents invoke run_deployed_task to trigger actions in Union 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 triggers execution of pre-deployed tasks in an external system (Union/Flyte workflow engine). While the description is empty, the name combined with server context and sibling tools clearly indicates it runs code/operations remotely. The effects depend on what the deployed task does, making it Execute rather than Write.
From the tool's definition Tool name 'run_deployed_task' indicates execution of a deployed task. Sibling tools include 'run_uv_script_remote' which explicitly performs remote execution, and 'get_run' / 'get_run_io' which retrieve execution results, confirming this server's primary…
Documented attack patterns abuse exactly the kind of access run_deployed_task gives an agent:
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 run_deployed_task:
{
"version": "1",
"default": "deny",
"tools": {
"run_deployed_task": {
"limits": [
{
"counter": "run_deployed_task_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_deployed_task 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_deployed_task. 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.
Register the Union MCP server in PolicyLayer and add a rule for run_deployed_task: 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.
run_deployed_task 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_deployed_task 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_deployed_task. 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_deployed_task 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.
Start from Union 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.
14 Union MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.