执行临时工作流实例 *This Tool has a 'MCP Resource'，please request ExecuteAdhocWorkflowInstance(MCP Resource) to get more examples for using this tool.
AI agents invoke ExecuteAdhocWorkflowInstance to trigger actions in Alibabacloud Dataworks. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
Name | string | Yes | 名称 |
Owner | string | Yes | 责任人的账号ID |
Tasks | array | Yes | 任务列表 |
BizDate | number | — | 业务日期。格式为时间戳 |
EnvType | string | — | 项目环境。- Prod：生产- Dev：开发 |
ProjectId | number | Yes | 项目ID |
Parameters from the server's own tool schema.
ExecuteAdhocWorkflowInstance triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts freeform code/query input (Tasks[].Script) · Accepts raw HTML/template content (Tasks[].Script.Content) · High parameter count (33 properties)
Attacks that exploit this kind of access
执行临时工作流实例 *This Tool has a 'MCP Resource'，please request ExecuteAdhocWorkflowInstance(MCP Resource) to get more examples for using this tool. It is categorised as a Execute tool in the Alibabacloud Dataworks MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
ExecuteAdhocWorkflowInstance accepts 6 parameters: Name, Owner, Tasks, BizDate, EnvType, ProjectId. Required: Name, Owner, Tasks, ProjectId. The full parameter table on this page comes from the server's own tool schema.
Register the Alibabacloud Dataworks MCP server in PolicyLayer and add a rule for ExecuteAdhocWorkflowInstance: 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 Alibabacloud Dataworks. Nothing to install.
ExecuteAdhocWorkflowInstance 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 ExecuteAdhocWorkflowInstance 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 ExecuteAdhocWorkflowInstance. 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.
ExecuteAdhocWorkflowInstance is provided by the Alibabacloud Dataworks MCP server (alibabacloud-dataworks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.