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 na...
This record as markdown: /tools/flowdot-llc-mcp-server/update-custom-node.md
What update_custom_node does on FlowDot MCP Server
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.
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 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().
Attacks that exploit this kind of access
The rule that runs update_custom_node safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FlowDot MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update_custom_node, this is the rule to start with:
update_custom_node stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect FlowDot MCP Server, apply this rule, and every update_custom_node call is checked against it from then on.
Questions about 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 }. It is categorised as a Write tool in the FlowDot MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FlowDot MCP Server MCP server in PolicyLayer and add a rule for update_custom_node: 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 FlowDot MCP Server. Nothing to install.
update_custom_node is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_custom_node 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 update_custom_node. 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.
update_custom_node is provided by the FlowDot MCP Server MCP server (flowdot-llc/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FlowDot MCP Server, and thousands of servers like it.
This server
Across the catalogue