neuron_request_approval
Ask a human to approve or reject an action over WhatsApp and get the decision back. The recipient replies approve/reject (optionally with a reason) or quotes the message. Use this to gate any action needing human sign-off (refunds, deploys, spend, publishing). Returns an approvalId; poll neuron_g...
This record as markdown: /tools/io-github-conquext-neuron/neuron-request-approval.md
What neuron_request_approval does on Neuron
AI agents call neuron_request_approval to retrieve information from Neuron without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
to | string | Yes | Recipient phone number (E.164/digits) or WhatsApp group JID |
apiKey | string | Yes | Bot API key with 'nrn_' prefix for authentication |
prompt | string | Yes | The approval question shown to the human |
context | string | — | Optional long-form details — stored in a shareable Neuron Note and linked from the WhatsApp message |
callback | object | — | Callback config. Omit for a poll-only flow (delivery scheme 'none'). |
metadata | object | — | Opaque data echoed back verbatim in the result/callback |
channelId | string | — | Optional WhatsApp channel override (UUID) |
idempotencyKey | string | — | Dedupe key — returns the existing approval on repeat |
expiresInSeconds | integer | — | Time to live before auto-expiry (default 86400, 60–604800) |
Parameters from the server's own tool schema.
Why neuron_request_approval is rated Low
Even though neuron_request_approval only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts freeform code/query input (callback.response.code) · Handles credentials or secrets (apiKey) · High parameter count (17 properties)
Attacks that exploit this kind of access
The rule that runs neuron_request_approval 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_request_approval, this is the rule to start with:
neuron_request_approval is read-only, so it stays allowed. 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_request_approval call is checked against it from then on.
Questions about neuron_request_approval
Ask a human to approve or reject an action over WhatsApp and get the decision back. The recipient replies approve/reject (optionally with a reason) or quotes the message. Use this to gate any action needing human sign-off (refunds, deploys, spend, publishing). Returns an approvalId; poll neuron_get_approval / neuron_list_approvals for the outcome, or supply a webhook in callback to be notified. Requires a bot API key ('nrn_' prefix). It is categorised as a Read tool in the Neuron MCP Server, which means it retrieves data without modifying state.
neuron_request_approval accepts 9 parameters: to, apiKey, prompt, context, callback, metadata, channelId, idempotencyKey, expiresInSeconds. Required: to, apiKey, prompt. 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_request_approval: 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_request_approval is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the neuron_request_approval 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_request_approval. 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_request_approval 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