neuron_audio_contact
Transcribe an audio recording and extract contact information (name, phone, email, notes, tags). Automatically saves the extracted contact to the organization's address book.
This record as markdown: /tools/io-github-conquext-neuron/neuron-audio-contact.md
What neuron_audio_contact does on Neuron
AI agents use neuron_audio_contact 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 |
|---|---|---|---|
audioBase64 | string | Yes | Base64-encoded audio data containing spoken contact information |
audioFormat | string | — | Audio format hint for decoding (default: 'webm') |
Parameters from the server's own tool schema.
Why neuron_audio_contact is rated Medium
This tool creates or updates contact records in the organization's address book, which is a write operation. The severity is medium because unauthorized creation of contacts could lead to data pollution, duplicate entries, or potential phishing/spoofing if fake contacts are added, but the impact is reversible (contacts can be deleted).
From the tool's definition Tool performs 'automatically saves the extracted contact to the organization's address book' which modifies data in a reversible manner by creating new contact records.
Attacks that exploit this kind of access
The rule that runs neuron_audio_contact 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_audio_contact, this is the rule to start with:
neuron_audio_contact 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_audio_contact call is checked against it from then on.
Questions about neuron_audio_contact
Transcribe an audio recording and extract contact information (name, phone, email, notes, tags). Automatically saves the extracted contact to the organization's address book. 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_audio_contact accepts 2 parameters: audioBase64, audioFormat. Required: audioBase64. 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_audio_contact: 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_audio_contact 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_audio_contact 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_audio_contact. 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_audio_contact 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