> For the complete documentation index, see [llms.txt](https://docs.nerovasystems.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nerovasystems.com/mcp-server/readme.md).

# MCP server

Nerova is API-first SaaS. Its remote Model Context Protocol (MCP) server lets authorized AI assistants operate the same API as your platform integration. MCP is an additional developer interface, not a separate product or a replacement for API authorization. One connection URL serves integrations:

```
https://api.nerovasystems.com/mcp
```

Sign in with your Nerova account, choose the permissions the assistant may use, and the assistant gets tools for exactly that grant — nothing more. Connections are Live only, mirroring API keys.

The first release is limited to Platform accounts serving human medical/clinic, salon/barber, and beauty businesses including nails. Existing tool names do not establish support for veterinary, other verticals, vaccination automation, or the deprecated customer WhatsApp payment flow. See [First-release scope](https://docs.nerovasystems.com/documentation/console/platform-access#first-release-scope). Tool retirement is a separate implementation change, not a result of this copy.

## How it works

* **Tools map one-to-one onto the published API.** Every tool corresponds to one operation of the `tenant-v1` contract and is derived mechanically from it, so the tool surface can never drift from the [API reference](https://docs.nerovasystems.com/documentation/api/reference).
* **You only see what you granted.** `tools/list` is filtered by the connection's permissions; tools whose scopes were not granted stay invisible. Every call is authorized again server-side and fails closed.
* **Same enforcement as the API.** Tool calls execute against `/api/v1/**` with your credential, so tenant grants, entitlement gating, [rate limits](https://docs.nerovasystems.com/documentation/api/rate-limits), and the [error catalog](https://docs.nerovasystems.com/documentation/api/error-catalog) apply unchanged. Tool errors carry the API's problem details, including the stable `code`.
* **Writes are safe by construction.** Mutations receive an automatic idempotency key per invocation, and destructive tools are flagged so MCP clients ask for confirmation first.

## Get started

1. [Connect a client](/mcp-server/connecting.md) — setup for Claude, VS Code, Cursor, and other MCP clients.
2. [Authentication and consent](/mcp-server/authentication.md) — the OAuth flow, the API-key alternative, and revocation.
3. [Tool reference](/mcp-server/tools.md) — every tool, grouped by permission area.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.nerovasystems.com/mcp-server/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.