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

# MCP server

> Let an AI assistant query your Recepta.ai workspace directly.

Recepta.ai exposes a [Model Context Protocol](https://modelcontextprotocol.io) server, so an AI assistant can query your workspace in natural language — "how many calls did we miss last week", "show me the transcript where the customer mentioned a leak" — without you building an integration.

## Endpoint

```text theme={null}
https://api.recepta.ai/mcp
```

Streamable HTTP transport, stateless. Authenticate with an [API key](/api-reference/authentication) in the `x-api-key` header. The key's permissions govern what the assistant can reach — a key without `calls:transcript` means no transcript access, regardless of what's asked for.

## Connecting a client

Most MCP clients take a URL and headers. In Claude Code:

```bash theme={null}
claude mcp add --transport http recepta https://api.recepta.ai/mcp \
  --header "x-api-key: $RECEPTA_API_KEY"
```

For other clients, consult their MCP configuration — you'll supply the URL above and the `x-api-key` header.

<Note>
  Add `x-location-id` as a second header to scope the whole session to one [location](/account/locations).
</Note>

## Available tools

### Calls

| Tool                  | Does                                                                   |
| --------------------- | ---------------------------------------------------------------------- |
| `list_calls`          | List calls, filtered by status, direction, type, agent, and date range |
| `get_call_details`    | Full detail for one call, including transcript and recording URL       |
| `get_call_transcript` | The transcript for a call                                              |
| `get_call_analytics`  | Aggregate call metrics                                                 |

### Contacts

| Tool             | Does                 |
| ---------------- | -------------------- |
| `list_clients`   | List contacts        |
| `search_clients` | Search contacts      |
| `get_client`     | Retrieve one contact |

### SMS

| Tool                     | Does                      |
| ------------------------ | ------------------------- |
| `list_sms_conversations` | List SMS conversations    |
| `get_sms_conversation`   | Retrieve one conversation |
| `search_sms_messages`    | Search across messages    |

### Campaigns

| Tool                    | Does                    |
| ----------------------- | ----------------------- |
| `list_campaigns`        | List outbound campaigns |
| `get_campaign_details`  | Detail for one campaign |
| `list_campaign_clients` | Contacts in a campaign  |

### Agents & analytics

| Tool                     | Does                        |
| ------------------------ | --------------------------- |
| `list_agents`            | List your agents            |
| `get_agent_details`      | Configuration for one agent |
| `list_knowledge_bases`   | List knowledge bases        |
| `get_dashboard_overview` | Headline workspace metrics  |
| `get_usage_stats`        | Usage against your plan     |

## Read-only by design

These tools query your workspace; they don't place calls, send messages, or modify records. An assistant connected this way can analyze what happened but can't act on your customers.

<Tip>
  Use a dedicated API key for MCP with read scopes only — `calls:read`, `contacts:read`, `sms:read`, `analytics:read`. Add `calls:transcript` only if you want the assistant reading what customers said.
</Tip>

## Worth asking it

* "What were the most common reasons callers were transferred to a human last month?"
* "Which calls ended without a booking, and what did the customer ask about?"
* "Compare booking rates across our locations this quarter."
* "Find SMS conversations where someone asked about pricing but never booked."

These are the questions that normally require exporting data and building a report. The answers point straight at what to fix — see [QA & learning](/receptionist/qa-and-learning).

<Warning>
  Call transcripts contain customer personal data. Connecting an assistant with transcript access means that data goes to whichever AI provider powers it. Confirm that's compatible with your privacy policy and customer commitments. See [Security & privacy](/account/security-and-privacy).
</Warning>

## Rate limits

MCP requests are rate limited per API key by plan tier, as the REST API is. See [Rate limits](/api-reference/rate-limits).