neuron_compose_message
Compose and send a new message to a phone number via a specific channel. Automatically creates a new conversation if one does not exist.
This record as markdown: /tools/io-github-conquext-neuron/neuron-compose-message.md
What neuron_compose_message does on Neuron
AI agents use neuron_compose_message 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 |
|---|---|---|---|
to | string | Yes | Recipient phone number (E.164 format, e.g., '2348012345678') |
text | string | Yes | Message text content |
mediaUrl | string | — | URL of media to attach (required for non-text message types) |
channelId | string | Yes | Unique identifier (UUID) of the WhatsApp channel to send through |
contactName | string | — | Display name for the recipient contact |
messageType | string | — | Type of message: 'text' (default), 'image', or 'document' |
Parameters from the server's own tool schema.
Why neuron_compose_message is rated Medium
This tool creates new messages and conversations, which are write operations (data creation). It is reversible in nature—messages can typically be deleted or conversations archived. The severity is medium because sending unsolicited messages at scale could be abusive (spam, harassment) but does not result in irreversible data loss or financial impact.
From the tool's definition Tool description explicitly states 'Compose and send a new message to a phone number via a specific channel.
Attacks that exploit this kind of access
The rule that runs neuron_compose_message 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_compose_message, this is the rule to start with:
neuron_compose_message 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_compose_message call is checked against it from then on.
Questions about neuron_compose_message
Compose and send a new message to a phone number via a specific channel. Automatically creates a new conversation if one does not exist. 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_compose_message accepts 6 parameters: to, text, mediaUrl, channelId, contactName, messageType. Required: to, text, channelId. 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_compose_message: 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_compose_message 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_compose_message 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_compose_message. 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_compose_message 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