# create_workflow

A write tool on the n8n MCP Server MCP server.

Agent View of the PolicyLayer registry record for `create_workflow`. HTML page: https://policylayer.com/tools/andhit-r-n8n-mcp/create-workflow

## Facts

- Tool: `create_workflow`
- Server: n8n MCP Server (`andhit-r/n8n-mcp`) — https://policylayer.com/tools/andhit-r-n8n-mcp.md
- Homepage: https://github.com/andhit-r/n8n-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why create_workflow is rated Medium

The name 'create_workflow' strongly implies creating a new workflow resource in n8n, which is a Write operation. The description is empty, so confidence is reduced. However, sibling tools follow clear naming conventions (create_tag, create_variable, delete_workflow, etc.), making it highly likely this tool creates a new workflow.

From the tool's own definition: "Tool name 'create_workflow' on a server that manages n8n workflows, executions, credentials, tags, and variables."

## Use case

AI agents use create_workflow to create or update resources in n8n MCP Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your n8n MCP Server environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches n8n MCP Server:

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

## Other tools on n8n MCP Server (21)

- `delete_credential` — Destructive — https://policylayer.com/tools/andhit-r-n8n-mcp/delete-credential.md
- `delete_execution` — Destructive — https://policylayer.com/tools/andhit-r-n8n-mcp/delete-execution.md
- `delete_tag` — Destructive — https://policylayer.com/tools/andhit-r-n8n-mcp/delete-tag.md
- `delete_variable` — Destructive — https://policylayer.com/tools/andhit-r-n8n-mcp/delete-variable.md
- `delete_workflow` — Destructive — https://policylayer.com/tools/andhit-r-n8n-mcp/delete-workflow.md
- `activate_workflow` — Execute — https://policylayer.com/tools/andhit-r-n8n-mcp/activate-workflow.md
- `deactivate_workflow` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/deactivate-workflow.md
- `get_audit_log` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/get-audit-log.md
- `get_credential` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/get-credential.md
- `get_execution` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/get-execution.md
- `get_workflow` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/get-workflow.md
- `list_credentials` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/list-credentials.md
- `list_executions` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/list-executions.md
- `list_tags` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/list-tags.md
- `list_variables` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/list-variables.md
- `list_workflows` — Read — https://policylayer.com/tools/andhit-r-n8n-mcp/list-workflows.md
- `create_credential` — Write — https://policylayer.com/tools/andhit-r-n8n-mcp/create-credential.md
- `create_tag` — Write — https://policylayer.com/tools/andhit-r-n8n-mcp/create-tag.md
- `create_variable` — Write — https://policylayer.com/tools/andhit-r-n8n-mcp/create-variable.md
- `update_tag` — Write — https://policylayer.com/tools/andhit-r-n8n-mcp/update-tag.md
- `update_workflow` — Write — https://policylayer.com/tools/andhit-r-n8n-mcp/update-workflow.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=andhit-r-n8n-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/andhit-r-n8n-mcp