> For the complete documentation index, see [llms.txt](https://help.sipgate.de/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.sipgate.de/conversation-intelligence/conversation-intelligence-en/connect-mcp-server.md).

# Connect MCP server

With the sipgate MCP server, you connect your call data directly to an AI assistant, e.g. Claude or ChatGPT, and ask your questions in the chat.

#### What can I do with the MCP server?

The sipgate MCP server connects your call data with an AI assistant that supports the Model Context Protocol (MCP). Instead of exporting data and loading it into an external tool, you ask your questions in chat and receive an analysis based on your current call data.

Examples of questions:

* “How did the average call duration per week develop in August?”
* “How many incoming calls over 2 minutes were assigned to the invoice topic?”
* “Which custom fields are set up in my account?”

Your AI assistant retrieves the relevant calls and calculates the analysis from them. Therefore, check important figures on a sample basis in the [Data Hub](broken://pages/1bf15d74eaab346d3bdd1fccf8e4b74dd27ca815).

#### What do I need for that?

* An MCP-capable client that supports its own MCP servers
* Call data for the queried period

#### What data is available?

The MCP server provides the metadata of your calls, not the content of the conversations:

* **Call data:** Time, direction, phone numbers, channel or endpoint, call result and whether a transcription is available
* **Times:** Call duration, waiting time, ringing time, handling time and after-call work time
* **AI analyses:** Subject, topics, playbooks as well as your custom fields, including summary
* **Selection values:** Which custom fields and filter values (e.g. subjects, playbooks) are present in your account

#### How do I connect the MCP server?

{% stepper %}
{% step %}

## Add MCP server

Open the settings for Connectors or MCP servers in your AI assistant and add a new custom server.
{% endstep %}

{% step %}

## Enter server URL

Enter as the server URL `https://api.sipgate.com/mcp` .
{% endstep %}

{% step %}

## Log in with sipgate

Sign in with your sipgate account via OAuth.
{% endstep %}

{% step %}

## Ask your first question

Ask your first question about your call data.
{% endstep %}
{% endstepper %}

#### Good to know

* **Filters:** As in the Data Hub, AND and OR cannot be mixed. For mixed logic, your AI assistant creates several queries and combines the results.
* **Privacy:** The retrieved data can be personal data, e.g. phone numbers, contact names and summaries. This data is processed by your AI provider. Check the legal basis and data processing agreement (see [Data protection](broken://pages/825b447ea55cbbf11355bd3143c076c3cf10c133)).
* **No performance evaluation:** Do not use the MCP server to evaluate individual employees.
* **Experimental:** The underlying interface (REST API v3) is marked as experimental and may still change.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.sipgate.de/conversation-intelligence/conversation-intelligence-en/connect-mcp-server.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.