Release a delayed query from the queue, allowing it to execute immediately. Use this to manually override throttles or resolve stuck queries when system resources are available. Provide either sessionNo (for specific session) or userName (for all that user
AI agents invoke release_delay_queue to trigger actions in Teradata Workload Management (WLM) MCP Server. 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 executes database queries by releasing them from a delay queue. The effects are not merely data retrieval (Read) or reversible modification (Write), but rather the triggering of potentially expensive or resource-intensive query execution that was deliberately throttled.
From the tool's definition The tool description states it will 'Release a delayed query from the queue, allowing it to execute immediately' and 'manually override throttles', which triggers execution of external database operations whose effects depend on which query/session is…
Documented attack patterns abuse exactly the kind of access release_delay_queue gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Teradata Workload Management (WLM) MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for release_delay_queue:
{
"version": "1",
"default": "deny",
"tools": {
"release_delay_queue": {
"limits": [
{
"counter": "release_delay_queue_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} release_delay_queue 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.
All 41 Teradata Workload Management (WLM) MCP Server tools →
Release a delayed query from the queue, allowing it to execute immediately. Use this to manually override throttles or resolve stuck queries when system resources are available. Provide either sessionNo (for specific session) or userName (for all that user. It is categorised as a Execute tool in the Teradata Workload Management (WLM) MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Teradata Workload Management (WLM) MCP Server MCP server in PolicyLayer and add a rule for release_delay_queue: 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 Teradata Workload Management (WLM) MCP Server. Nothing to install.
release_delay_queue 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 release_delay_queue 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 release_delay_queue. 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.
release_delay_queue is provided by the Teradata Workload Management (WLM) MCP Server MCP server (teradata-labs/mcp-server-teradata-wlm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Teradata Workload Management (WLM) MCP Server, 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.
41 Teradata Workload Management (WLM) MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.