Query a running workflow execution using a named query handler.
AI agents invoke temporal.workflow.query to trigger actions in Temporal. 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.
While 'query' sounds like a read operation, in Temporal a workflow query invokes a named query handler on a running workflow execution. This is an active operation that triggers code execution within the workflow process. It's not purely read-only data retrieval — it executes a handler function on a live workflow.
From the tool's definition Query a running workflow execution using a named query handler
Documented attack patterns abuse exactly the kind of access temporal.workflow.query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Temporal, and nothing reaches the server without passing your rules. This is the rule we recommend for temporal.workflow.query:
{
"version": "1",
"default": "deny",
"tools": {
"temporal.workflow.query": {
"limits": [
{
"counter": "temporal.workflow.query_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}temporal.workflow.query 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.
Query a running workflow execution using a named query handler. It is categorised as a Execute tool in the Temporal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Temporal MCP server in PolicyLayer and add a rule for temporal.workflow.query: 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 Temporal. Nothing to install.
temporal.workflow.query 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 temporal.workflow.query 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 temporal.workflow.query. 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.
temporal.workflow.query is provided by the Temporal MCP server (stevekinney/temporal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Temporal, 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.
28 Temporal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.