RubiConnect

create_flow

Creates a new multi-step conversation flow on the ReactFlow canvas for an agent. Automatically creates any inline rich card/carousel/text templates, normalizes node/edge handles, auto-layouts the graph visually, validates all branches, and saves the flow.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "nodes": "<nodes>",
      "edges": "<edges>"
    },
    "name": "create_flow"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Human-readable name for the new flow (e.g. "VIP Appointment Follow-Up").
`edges`	Yes	Directed edges connecting source nodes/handles to target nodes.
`nodes`	Yes	List of flow nodes. If the start node is omitted, one is automatically prepended.
`agentId`	No	Agent ID or display name. Defaults to the active agent in context.
`folderId`	No	Optional existing flow folder ID.
`autoLayout`	No	Automatically arrange node coordinates cleanly top-to-bottom (default true when positions are omitted).
`folderName`	No	Optional flow folder name (automatically created if it does not exist yet; inline templates created with this flow are also organized into a matching template folder unless templateFolderName is specified).
`description`	No	Short summary of what this flow does.
`templateFolderId`	No	Optional template folder ID for inline templates created with this flow.
`templateFolderName`	No	Optional template folder name for inline templates created with this flow (defaults to folderName when folderName is set).

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 2, 2026

addedInput schema / properties / nodes / items / properties / data / properties / triggerConnectionId

Added value: +{
+  "description": "Optional calendar connection ID filter ('all' or a specific connectionId).",
+  "type": "string"
+}

addedInput schema / properties / nodes / items / properties / data / properties / triggerEventSources

Added value: +{
+  "description": "Optional list of checked Event Sources for calendar triggers (e.g. ['external_only', 'ai_agent:<aiAgentId>', '<rubiAppId>']). Omit or leave with triggerRubiAppId='all' for all sources.",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

addedInput schema / properties / nodes / items / properties / data / properties / triggerRubiAppId

Added value: +{
+  "description": "Optional event source / Rubi App ID filter for calendar triggers ('all', 'none', 'custom', 'external_only', 'ai_agent:<aiAgentId>', or a specific Rubi App ID).",
+  "type": "string"
+}

Changed3 schema fields changedNov 2, 2026

changedInput schema / properties / folderName / description

Previous value: -"Optional flow folder name (automatically created if it does not exist yet)."New value: +"Optional flow folder name (automatically created if it does not exist yet; inline templates created with this flow are also organized into a matching template folder unless templateFolderName is specified)."

addedInput schema / properties / templateFolderId

Added value: +{
+  "description": "Optional template folder ID for inline templates created with this flow.",
+  "type": "string"
+}

addedInput schema / properties / templateFolderName

Added value: +{
+  "description": "Optional template folder name for inline templates created with this flow (defaults to folderName when folderName is set).",
+  "type": "string"
+}

AddedNov 2, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description carries the burden and does meaningful work: it discloses cascading side effects (auto-creating inline card/carousel/text templates), normalization of node/edge handles, auto-layout, branch validation, and persistence. It stops short of stating permission requirements, what happens when validation fails, or whether the write is atomic.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence, front-loaded with the core action, then a compact enumeration of cascading behaviors. No padding or restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 10-parameter mutation tool with no output schema, the description conveys the important behavioral cascade and that the flow is saved. It omits what is returned (e.g., new flow ID) and the failure mode when branch validation rejects the graph, which an agent would want to know.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are already documented in detail. The description adds only indirect signal — 'auto-layouts the graph visually' maps to the autoLayout/position parameters, and the inline-template mention maps to inlineTemplate. Baseline 3 is appropriate given the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb+resource: 'Creates a new multi-step conversation flow on the ReactFlow canvas for an agent.' It names the canvas surface and the object type, which distinguishes it from update_flow (modify existing) and clone_flow (duplicate). An agent can tell what this creates without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Creation-vs-update usage is implied by the verb, and the auto-creation of inline templates hints that callers need not pre-create templates via create_template. However, no sibling is named and no when-not condition is given (e.g., 'do not use to modify an existing flow — use update_flow').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All RubiConnect tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?