# neuron_create_flow

Create a new automation flow. A flow is a directed graph of nodes connected by edges. The graph MUST start with at least one trigger node (entry point). Edges connect nodes via output handles. BEFORE BUILDING: call neuron_get_flow_catalog and read its reference — it carries the JSON shapes you cannot guess: the ConditionGroup + operator list for branch/filter/switch conditions, the cases/assignments/weekdays composite shapes, the handle wiring map, and copy-ready examples. Condition field on a logic node must be a {{template}} (e.g. '{{trigger.text}}'); on a trigger's config.conditions it is a raw payload path (e.g. 'text'). AFTER SAVING: the flow always saves, but the response includes a warnings array flagging likely bugs (unknown node type, missing required field, malformed conditions/cases/assignments, edges wired to a handle a node never emits, missing trigger). Always check it and fix any warnings — a warning means that part will silently no-op at run time. TEMPLATE RESOLUTION: Node config values support {{…}} templates resolved at runtime: {{trigger.text}} — the triggering message text {{trigger.contactPhone}} — the sender's phone {{trigger.senderName}} — the sender's name {{vars.myVar}} — a variable set by logic.set_variable {{nodes.n_abc.output.text}} — output from a previous node {{= amount * 1.1 }} — inline expression (arithmetic, comparisons, ternary) ERROR HANDLING: Any node's config can include __errorHandling: { continueOnFail: true, retryCount: 3, retryDelayMs: 1000 } to retry on failure with exponential backoff and/or continue on the 'error' handle instead of failing the run. WIRING RULES: - logic.branch: 'true' and 'false' handles - logic.switch / logic.ai_router: one handle per case id, plus 'default' - logic.wait_for_reply: 'default' (replied) and 'timeout' - logic.wait_for_approval: 'approved', 'rejected', 'timeout' - logic.wait_first_of: 'reply', 'event', 'timeout' - logic.loop: 'loop' (body) and 'done' - action.lookup_contact: 'found' and 'not_found' - action.call_flow: 'default' (returned), 'timeout', 'error' - All other nodes: 'default' handle (or 'error' when continueOnFail is on)

Agent View of the PolicyLayer registry record for `neuron_create_flow`. HTML page: https://policylayer.com/tools/io-github-conquext-neuron/neuron-create-flow

## Facts

- Tool: `neuron_create_flow`
- Server: Neuron (`neuron-mcp-server`) — https://policylayer.com/tools/io-github-conquext-neuron.md
- Install: `npx -y neuron-mcp-server`
- Homepage: https://github.com/conquext/neuron
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: *
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `name` | string | yes | Human-readable name for the flow. |
| `graph` | object | no | The flow graph — nodes and edges. Omit to create an empty flow (edit later in the UI). |
| `enabled` | boolean | no | Whether the flow should be active immediately (default: false). |
| `description` | string | no | Optional description of what the flow does. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "neuron_create_flow",
    "arguments": {
      "name": "<name>"
    }
  }
}
```

## Why neuron_create_flow is rated Medium

An AI agent can call neuron_create_flow faster than any human can review: one bad instruction and it creates or modifies resources in Neuron by the hundred, each call as confident as the last.

Risk signals: High parameter count (17 properties)

## Use case

AI agents use neuron_create_flow to create or update resources in Neuron, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Neuron environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Neuron:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "neuron_create_flow": {
      "limits": [
        {
          "counter": "neuron_create_flow_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Neuron (400)

- `neuron_cancel_approval` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-cancel-approval.md
- `neuron_cancel_booking` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-cancel-booking.md
- `neuron_cancel_flow_run` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-cancel-flow-run.md
- `neuron_cancel_scheduled_message` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-cancel-scheduled-message.md
- `neuron_clear_chat` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-clear-chat.md
- `neuron_clear_media` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-clear-media.md
- `neuron_delete_ad_request` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-ad-request.md
- `neuron_delete_blog_post` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-blog-post.md
- `neuron_delete_bot` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-bot.md
- `neuron_delete_broadcast` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-broadcast.md
- `neuron_delete_calendar` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-calendar.md
- `neuron_delete_campaign` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-campaign.md
- `neuron_delete_channel` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-channel.md
- `neuron_delete_contact` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-contact.md
- `neuron_delete_contact_list` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-contact-list.md
- `neuron_delete_event` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-event.md
- `neuron_delete_event_type` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-event-type.md
- `neuron_delete_flow` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-flow.md
- `neuron_delete_flow_run` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-flow-run.md
- `neuron_delete_kb_entry` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-kb-entry.md
- `neuron_delete_knowledge_base` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-knowledge-base.md
- `neuron_delete_list_campaign` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-list-campaign.md
- `neuron_delete_message` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-message.md
- `neuron_delete_newsletter` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-newsletter.md
- `neuron_delete_outbound_webhook` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-outbound-webhook.md
- `neuron_delete_override` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-override.md
- `neuron_delete_persona` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-persona.md
- `neuron_delete_product` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-product.md
- `neuron_delete_sms_campaign` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-sms-campaign.md
- `neuron_delete_social_channel` — Destructive — https://policylayer.com/tools/io-github-conquext-neuron/neuron-delete-social-channel.md
- …and 370 more: https://policylayer.com/tools/io-github-conquext-neuron.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=io-github-conquext-neuron · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/io-github-conquext-neuron