> ## Documentation Index
> Fetch the complete documentation index at: https://agents.concierca.ch/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect via MCP

> The human setup guide: what MCP is, your workspace endpoint, connecting Claude and ChatGPT, getting a key, and your first calls.

**MCP (Model Context Protocol) is the standard way an AI client plugs into your workspace.** Connect Claude, ChatGPT, or any MCP-capable client once, and it can read your data and act inside Concierca AI — always under the same tenant, departments, roles, and governance you already use in the app.

<Note>
  Every call runs **server-side as the user who owns the key**. Reads are filtered to what that user may see; writes need the matching per-tool grant. Secrets and OAuth flows never travel the model channel.
</Note>

## Your endpoint

Point any MCP client at your workspace:

```text theme={null}
https://app.concierca.ch/api/mcp/v1
```

This one endpoint exposes the whole surface — agents, missions, data, knowledge, memory, skills, approvals, and the market-intelligence vertical. (There is also a standalone vertical-only endpoint, `https://app.concierca.ch/api/mcp/watchinside`, for the market-intelligence tools on their own.)

## Get your key

Both ways to connect start in the app under **Settings › MCP Access**:

* **OAuth (recommended for a person).** Add the server by URL in your client and approve in the browser — no key to copy or store. A Company-Admin connect grants the full surface; a Member connect grants the read-only baseline.
* **API key.** Generate a key and pass it as a bearer token. Best for headless agents and the [CLI](/guide/mcp-cli). When you generate it, you pick exactly which tools the key may call (a per-tool allowlist).

## Connect from Claude (Desktop / Code)

Add the server to your MCP client config, pointing at the endpoint with your key:

```json theme={null}
{
  "mcpServers": {
    "concierca": {
      "url": "https://app.concierca.ch/api/mcp/v1",
      "headers": { "Authorization": "Bearer <your-mcp-key>" }
    }
  }
}
```

For OAuth-capable clients, add the server by URL and complete the browser approval instead of pasting a key.

## Connect from ChatGPT

Add a **connector** pointing at `https://app.concierca.ch/api/mcp/v1` and authorize it.

<Warning>
  ChatGPT loads the tool list only when a connector is **created**, and does not refresh it live. After your grants change (new tools, a reconnect), **delete the connector and add it again** to pick up the current tool set — re-login or "reload" is not enough.
</Warning>

## Your first calls

Ground every session before acting:

1. **`whoami`** — confirms your identity, role, tenant, and exactly which tools your key may use.
2. **`get_context`** — returns your Operating Manual: the always-load governance and knowledge block.
3. **`guardrails_get`** — the governance rules to honor; over MCP these are pull-only, so fetch them at session start.

From there, browse [Every MCP Tool](/guide/mcp-tools) for the full catalog of what you can do.

## Reconnecting

Reconnecting inherits your existing scopes and deactivates the previous key — you never lose access by reconnecting, and old keys stop working. Read-only tools shipped after your first connect are added automatically; write tools are never re-added silently.

***

Driving Concierca as an AI client rather than setting it up by hand? The [**For AI Agents**](/api/ai/operating-contract) guide turns these first calls into a full operating contract — session start, the rule to discover before guessing, and every intent mapped to a tool sequence.