neuron_bot_api_send
Send an outbound message through the bot API to a specified phone number. Supports text and media messages. Requires a valid API key.
This record as markdown: /tools/io-github-conquext-neuron/neuron-bot-api-send.md
What neuron_bot_api_send does on Neuron
AI agents use neuron_bot_api_send 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's phone number (E.164 format, e.g., '+2348012345678') |
apiKey | string | Yes | Bot API key with 'nrn_' prefix for authentication |
message | string | Yes | The message text to send to the recipient |
mediaUrl | string | — | Public URL of the media file to attach (required for non-text message types) |
channelId | string | — | Unique identifier (UUID) of a specific WhatsApp channel to send from. Uses the bot's primary channel if omitted. |
messageType | string | — | Type of message to send: 'text', 'image', 'video', 'audio', or 'document' (default: 'text') |
Parameters from the server's own tool schema.
Why neuron_bot_api_send is rated Medium
This tool sends outbound WhatsApp messages to phone numbers, which is a Write operation (creates new message records and delivers communications). Severity is high because a misused agent could send unsolicited, harmful, or spam messages to arbitrary phone numbers at scale via the bot API, potentially causing reputational, legal, or privacy harms.
From the tool's definition Send an outbound message through the bot API to a specified phone number. Supports text and media messages.
Risk signalsHandles credentials or secrets (apiKey)
Attacks that exploit this kind of access
The rule that runs neuron_bot_api_send 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_bot_api_send, this is the rule to start with:
neuron_bot_api_send 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_bot_api_send call is checked against it from then on.
Questions about neuron_bot_api_send
Send an outbound message through the bot API to a specified phone number. Supports text and media messages. Requires a valid API key. 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_bot_api_send accepts 6 parameters: to, apiKey, message, mediaUrl, channelId, messageType. Required: to, apiKey, message. 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_bot_api_send: 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_bot_api_send 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_bot_api_send 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_bot_api_send. 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_bot_api_send 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