Neuratel AI — MCP Server
Official MCP Server for Neuratel Studio — control your voice AI platform through natural language from Claude, Cursor, Windsurf, and any MCP-compatible assistant.
46 hand-crafted tools across 11 domains. Every destructive operation carries an explicit cost warning.
Quick Start
NEURATEL_API_KEY=nk_live_... uvx neuratelai-mcp@latest
Or install permanently:
pip install neuratelai-mcp
Claude Desktop Setup
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"neuratel": {
"command": "uvx",
"args": ["neuratelai-mcp@latest"],
"env": {
"NEURATEL_API_KEY": "nk_live_your_key_here"
}
}
}
}
Restart Claude Desktop. You'll see neuratel in the tools panel with 46 tools available.
Claude Code
claude mcp add neuratel -e NEURATEL_API_KEY=nk_live_... -- uvx neuratelai-mcp@latest
Cursor / Windsurf
Add to ~/.cursor/mcp.json (Cursor) or Codeium MCP config (Windsurf):
{
"mcpServers": {
"neuratel": {
"command": "uvx",
"args": ["neuratelai-mcp@latest"],
"env": {
"NEURATEL_API_KEY": "nk_live_your_key_here"
}
}
}
}
HTTP / SSE Transport
For remote deployment or web-based clients:
NEURATEL_API_KEY=nk_live_... neuratelai-mcp --transport http --port 8000
Connect to http://your-host:8000/mcp.
Environment Variables
| Variable | Required | Default |
|---|---|---|
NEURATEL_API_KEY |
Yes | — |
NEURATEL_BASE_URL |
No | https://api.neuratel.ai/v1 |
Tools
| Domain | Count | What you can do |
|---|---|---|
| Agents | 8 | Create, list, inspect, update, delete, duplicate agents; list templates; get required variables |
| Calls | 5 | Place calls, list/get calls, monitor live sessions, hang up |
| Campaigns | 6 | Full campaign lifecycle — create, start, pause, stop |
| Conversations | 8 | Unified inbox — list, get, send messages, timeline, analytics, variables |
| DNC | 6 | Check, list, add, delete entries; get/update settings |
| Numbers | 3 | List numbers, assign and unassign agents |
| Knowledge Base | 4 | Add content from text or URL, attach to agent |
| Billing | 2 | Check balance, view usage |
| Webhooks | 2 | Create and list event subscriptions |
| Analytics | 1 | Combined voice + chat dashboard KPIs |
| Variables | 1 | System variables catalog for dynamic_variables validation |
Requirements
Python 3.11+ · uv recommended
Links
Release files for neuratelai-mcp 0.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| neuratelai_mcp-0.3.0.tar.gz | 23.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| neuratelai_mcp-0.3.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 55.2 kB
Release files / neuratelai_mcp-0.3.0.tar.gz
| Download URL | neuratelai_mcp-0.3.0.tar.gz |
|---|---|
| Size | 23.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
14df0154e60632274753661cc394ab45edb787dd122b509fc94c5c4e6712b8f1
|
|
BLAKE2b-256 checksum How to use checksums |
8a51b2d46c8efdaec10c1c0646a5443737e195d89a18de92e9bf36ec094e685a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 8, 2026.
Transparency logRelease files / neuratelai_mcp-0.3.0-py3-none-any.whl
| Download URL | neuratelai_mcp-0.3.0-py3-none-any.whl |
|---|---|
| Size | 32.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6d65de43104b2956ee03befcf7167f9f1599ad1605a08586f13f1566813088fa
|
|
BLAKE2b-256 checksum How to use checksums |
a92efa401ee72f30e56265fdb0e97b3616b1cd27a4715f8ca20581c4f82eaf5a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jun 8, 2026.
Transparency log