neuron_create_task
Create a scheduled autonomous task for a bot. The instruction is a self-contained, natural-language directive the bot executes with its tools (find stale conversations, message contacts, schedule follow-ups, etc.). Sends are always screened against Do-Not-Contact, a per-run cap, and a no-repeat w...
This record as markdown: /tools/io-github-conquext-neuron/neuron-create-task.md
What neuron_create_task does on Neuron
AI agents use neuron_create_task 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
botId | string | Yes | UUID of the bot |
title | string | Yes | Short title for the task |
config | object | — | Safety / execution config for the task. |
enabled | boolean | — | Whether the task is active (default true). |
schedule | object | — | Schedule payload matching scheduleKind. cron: { time: 'HH:MM', days?: number[] } (0=Sunday..6=Saturday; empty/omitted = every day). interval: { everyMinutes: nu |
timezone | string | — | IANA timezone (e.g. Africa/Lagos). Defaults to UTC. |
instruction | string | Yes | What the task should do, in natural language (self-contained; preserve any exact message copy verbatim). |
scheduleKind | string | Yes | cron = recurring at a clock time (slot); interval = every N minutes; once = a single future moment; manual = only runs on demand. |
Parameters from the server's own tool schema.
Why neuron_create_task is rated Medium
An AI agent can call neuron_create_task 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 signalsHigh parameter count (14 properties)
Attacks that exploit this kind of access
The rule that runs neuron_create_task safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Neuron, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For neuron_create_task, this is the rule to start with:
neuron_create_task 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 Neuron, apply this rule, and every neuron_create_task call is checked against it from then on.
Questions about neuron_create_task
Create a scheduled autonomous task for a bot. The instruction is a self-contained, natural-language directive the bot executes with its tools (find stale conversations, message contacts, schedule follow-ups, etc.). Sends are always screened against Do-Not-Contact, a per-run cap, and a no-repeat window. It is categorised as a Write tool in the Neuron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
neuron_create_task accepts 8 parameters: botId, title, config, enabled, schedule, timezone, instruction, scheduleKind. Required: botId, title, instruction, scheduleKind. The full parameter table on this page comes from the server's own tool schema.
Register the Neuron MCP server in PolicyLayer and add a rule for neuron_create_task: 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 Neuron. Nothing to install.
neuron_create_task 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 neuron_create_task 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 neuron_create_task. 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.
neuron_create_task is provided by the Neuron MCP server (neuron-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Neuron, and thousands of servers like it.
This server
Across the catalogue