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

# GermainUX MCP Server

> MCP Server: connect AI assistants and agents to GermainUX through the built-in Model Context Protocol (MCP) Server to query monitoring, analytics, and insights.

Components
[`Engine`](https://docs.germainux.com/deploy/germain-ux-engine)

Availability
TODO: version or later

> [card] [Overview](#overview)
>
> What the MCP Server does

> [card] [Available Tools](#available-tools)
>
> What AI agents can access

> [card] [Connect an AI Client](#connect-an-ai-client)
>
> Claude, Cursor and others

> [card] [Security](#security-and-access-control)
>
> Access control and privacy

> [!WARNING]
>
> Draft: items marked **TODO** need to be confirmed by the GermainUX team before publishing.

## Overview

GermainUX now includes a built-in **MCP Server**. The [Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open standard that lets AI assistants and agents connect to external tools and data sources.

With the GermainUX MCP Server, an MCP-compatible AI client can use GermainUX monitoring, analytics, and insights as context, so its answers are grounded in your real user, workflow, and technology data.

> [!NOTE]
>
> AI is only as accurate as the data behind it. The MCP Server gives AI agents access to the deep, contextual, and actionable data that GermainUX collects, rather than relying on prompts alone.

## Examples

### MCP Server for Salesforce

Watch how to use the GermainUX MCP Server with Salesforce:

[GermainUX MCP Server for Salesforce](https://www.youtube.com/embed/HZymsirsjPU)

You can also [watch it on YouTube](https://youtu.be/HZymsirsjPU).

### MCP Server for Shopify

Watch how to use the GermainUX MCP Server with Shopify:

[GermainUX MCP Server for Shopify](https://www.youtube.com/embed/7JfltkCBafw)

You can also [watch it on YouTube](https://youtu.be/7JfltkCBafw).

## Use Cases

* Ask an AI assistant what the top user frictions were in an application over a given period.
* Investigate an alert or SLA violation from your AI assistant or IDE.
* Summarize sessions, errors, or business-process issues affecting a group of users.
* Retrieve KPI values and trends to include in an analysis or report.
* Let an AI agent check GermainUX data before suggesting a fix or next step.

TODO: confirm and adjust the use cases supported in this release.

## Available Tools

The MCP Server exposes GermainUX capabilities to AI clients as MCP tools.

| Tool | Description |
| - | - |
| TODO | TODO: for example, search sessions, get KPI values, list alerts, get session summary |

TODO: list each tool, its parameters, and the data it returns.

## Prerequisites

* GermainUX TODO: version or later.
* A GermainUX user account with permission to the data the AI client will access.
* An MCP-compatible AI client (TODO: confirm supported clients, for example Claude, Cursor, ChatGPT, VS Code).
* Network access from the AI client to the GermainUX MCP Server endpoint.

## Enable the MCP Server

**1. Open the MCP Server settings**

TODO: menu path in GermainUX, for example **Settings > AI > MCP Server**.

**2. Enable the MCP Server**

TODO: describe the enable option and any related settings.

**3. Create credentials**

TODO: describe how to create an API token or configure OAuth for the AI client.

**4. Copy the endpoint URL**

TODO: endpoint format, for example `https://<your-germainux-host>/TODO`.

## Connect an AI Client

Add the GermainUX MCP Server to your AI client's MCP configuration. The exact steps depend on the client.

TODO: confirm the transport (for example Streamable HTTP) and authentication header.

```json theme={null}
{
  "mcpServers": {
    "germainux": {
      "url": "https://<your-germainux-host>/TODO",
      "headers": {
        "Authorization": "Bearer <your-token>"
      }
    }
  }
}
```

After the client connects, ask it a question about your GermainUX data to confirm that the tools are available.

## Security and Access Control

* The MCP Server respects GermainUX user permissions and team-based visibility (TODO: confirm).
* Sensitive data [masking and anonymization](https://docs.germainux.com/management/compliance-privacy-and-security/data-privacy.md) settings continue to apply (TODO: confirm).
* Credentials should be stored securely and rotated regularly.
* Data returned to an online LLM is processed by that LLM provider. Review your organization's AI policies before connecting.

See [AI Governance](https://docs.germainux.com/management/compliance-privacy-and-security/ai-governance.md) for how GermainUX handles AI security and responsible use.

## Related Documentation

> [card] [AI Settings](https://docs.germainux.com/management/ai-settings.md)
>
> Configure GermainUX AI

> [card] [AI-Driven Insights](https://docs.germainux.com/analytics/ai-driven-insights.md)
>
> Insights and recommendations

> [card] [Configure with WebMCP](https://docs.germainux.com/management/configure-with-webmcp.md)
>
> Configure GermainUX with a browser agent

> [card] [WebMCP Monitoring](https://docs.germainux.com/integrations/browser-monitoring/webmcp-monitoring.md)
>
> Monitor WebMCP activity in browsers

## Get Help

> [card] [Contact GermainUX Support](https://docs.germainux.com/getting-started/support.md)
>
> The GermainUX team helps you get up and running faster, empower your team, turn data into actionable insights, and optimize performance to deliver measurable business outcomes.

> [card] Can't Find What You Need?
>
> Search all GermainUX docs with **Ctrl + K**, or use the feedback buttons at the bottom of this page to tell us what is missing.

The content of this document is proprietary to GERMAIN SOFTWARE.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.