# update_custom_node

Update an existing custom node. Only provide fields you want to change. When updating script_code, remember: - Must define: function processData(inputs, properties, llm) { return { OutputName: value }; } - Valid dataTypes: text, number, boolean, json, array, any - Return keys must match output names exactly (case-sensitive) LLM CAPABILITY: Set llm_enabled: true to enable AI/LLM calls in your custom node. - Users will see Quick Select buttons (FlowDot, Simple, Capable, Complex) - Your script can call llm.call({ prompt, systemPrompt, temperature, maxTokens }) - Response: { success, response, error, provider, model, tokens }

Agent View of the PolicyLayer registry record for `update_custom_node`. HTML page: https://policylayer.com/tools/flowdot-llc-mcp-server/update-custom-node

## Facts

- Tool: `update_custom_node`
- Server: FlowDot MCP Server (`flowdot-llc/mcp-server`) — https://policylayer.com/tools/flowdot-llc-mcp-server.md
- Homepage: https://github.com/flowdot-llc/mcp-server
- 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": "update_custom_node",
    "arguments": {}
  }
}
```

## Why update_custom_node is rated Medium

This tool updates code that will be executed in the FlowDot platform, making it a Write action (reversible modification of data/code). Severity is high because malicious script_code could compromise workflow execution, data handling, or integrate unauthorized LLM calls. Confidence is high due to explicit mention of script_code updates and function definition requirements.

From the tool's own definition: "Tool description states 'Update an existing custom node' and allows modification of 'script_code' which can execute arbitrary JavaScript functions (processData) and make LLM API calls via llm.call()."

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on FlowDot MCP Server (206)

- `browser_act` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/browser-act.md
- `cancel_execution` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/cancel-execution.md
- `delete_agent_character` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-agent-character.md
- `delete_app` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-app.md
- `delete_app_file` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-app-file.md
- `delete_connection` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-connection.md
- `delete_custom_node` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-custom-node.md
- `delete_goal` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-goal.md
- `delete_goal_milestone` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-goal-milestone.md
- `delete_goal_task` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-goal-task.md
- `delete_image` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-image.md
- `delete_input_preset` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-input-preset.md
- `delete_knowledge_category` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-knowledge-category.md
- `delete_knowledge_document` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-knowledge-document.md
- `delete_node` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-node.md
- `delete_recipe` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-recipe.md
- `delete_recipe_step` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-recipe-step.md
- `delete_recipe_store` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-recipe-store.md
- `delete_workflow` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/delete-workflow.md
- `email_delete` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/email-delete.md
- `mcp__flowdot__delete_agent_toolkit` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/mcp--flowdot--delete-agent-toolkit.md
- `mcp__flowdot__delete_toolkit_tool` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/mcp--flowdot--delete-toolkit-tool.md
- `mcp__flowdot__uninstall_toolkit` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/mcp--flowdot--uninstall-toolkit.md
- `panic_clear` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/panic-clear.md
- `revoke_kb_access` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/revoke-kb-access.md
- `unlink_property_kb_source` — Destructive — https://policylayer.com/tools/flowdot-llc-mcp-server/unlink-property-kb-source.md
- `browser_launch` — Execute — https://policylayer.com/tools/flowdot-llc-mcp-server/browser-launch.md
- `browser_navigate` — Execute — https://policylayer.com/tools/flowdot-llc-mcp-server/browser-navigate.md
- `browser_sequence` — Execute — https://policylayer.com/tools/flowdot-llc-mcp-server/browser-sequence.md
- `browser_wait_for` — Execute — https://policylayer.com/tools/flowdot-llc-mcp-server/browser-wait-for.md
- …and 176 more: https://policylayer.com/tools/flowdot-llc-mcp-server.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=flowdot-llc-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/flowdot-llc-mcp-server