Get a deployed task on the remote Flyte cluster.
AI agents call get_deployed_task to retrieve information from Union MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about a deployed task from a remote Flyte cluster. It performs a read-only query operation with no side effects—no code execution, no data modification, and no irreversible actions. The verb 'Get' and the absence of language suggesting execution (e.g., 'run', 'execute', 'trigger') confirm this is a Read operation with low blast radius.
From the tool's definition Tool name 'get_deployed_task' and description 'Get a deployed task on the remote Flyte cluster' indicate retrieval of task metadata/configuration without modification or execution.
Documented attack patterns abuse exactly the kind of access get_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 get_deployed_task:
{
"version": "1",
"default": "deny",
"tools": {
"get_deployed_task": {}
}
}get_deployed_task is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get a deployed task on the remote Flyte cluster. It is categorised as a Read tool in the Union MCP MCP Server, which means it retrieves data without modifying state.
Register the Union MCP server in PolicyLayer and add a rule for get_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.
get_deployed_task is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_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 get_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.
get_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.