refine_cloudflow
Refines an existing CloudFlow using natural language. Streams progress and returns the answer and conversationId; normally no flowId is returned. A plan or clarification question may save nothing. Reusing conversationId continues that conversation. Generated codeNode code can pass validation and ...
This record as markdown: /tools/doit/refine-cloudflow.md
What refine_cloudflow does on Doit
AI agents invoke refine_cloudflow to trigger actions in Doit. 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 |
|---|---|---|---|
flowId | string | Yes | The ID of the CloudFlow flow to refine |
question | string | Yes | The instruction or question to refine or rebuild the flow |
conversationId | string | — | Optional conversation ID for multi-turn sessions |
Parameters from the server's own tool schema.
Why refine_cloudflow is rated High
refine_cloudflow 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.
Attacks that exploit this kind of access
The rule that runs refine_cloudflow safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Doit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For refine_cloudflow, this is the rule to start with:
refine_cloudflow 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Doit, apply this rule, and every refine_cloudflow call is checked against it from then on.
Questions about refine_cloudflow
Refines an existing CloudFlow using natural language. Streams progress and returns the answer and conversationId; normally no flowId is returned. A plan or clarification question may save nothing. Reusing conversationId continues that conversation. Generated codeNode code can pass validation and fail silently or error at run time, so a successful build shows only that a draft was saved. export_cloudflow_flow returns the saved code; a completed test run's per-node output shows whether it works. Test runs execute real actions, including on drafts. It is categorised as a Execute tool in the Doit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
refine_cloudflow accepts 3 parameters: flowId, question, conversationId. Required: flowId, question. The full parameter table on this page comes from the server's own tool schema.
Register the Doit MCP server in PolicyLayer and add a rule for refine_cloudflow: 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 Doit. Nothing to install.
refine_cloudflow 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 refine_cloudflow 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 refine_cloudflow. 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.
refine_cloudflow is provided by the Doit MCP server (@doitintl/doit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Doit, and thousands of servers like it.
This server
Across the catalogue