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

# Troubleshoot the Dscout MCP

While hopefully a rare occurrence, you may run into issues when using the Dscout MCP. Refer to the errors or situations below for guidance on how to get moving again:

<details>

<summary>Authentication error</summary>

The Dscout MCP uses your standard Dscout credentials for authentication. Verify you're entering the correct email and password, or using the correct SSO method, when prompted.

</details>

<details>

<summary>Account not approved/available</summary>

The Dscout MCP only works on Dscout accounts that it's been granted access to. If your AI tool has trouble accessing your Dscout account, reach out to your Dscout Account Owner or Account Director.

</details>

<details>

<summary>Figma/prototype error</summary>

If the MCP is struggling with a Figma file or prototype, there may be a permissions issue with the file itself. Ensure you have access to the file yourself, then verify your AI tool also has access.

For example, you may need to reconnect your Figma connector if you're having trouble accessing a Figma prototype.

</details>

<details>

<summary>Can’t draft a study type other than a usability test</summary>

Drafting media surveys, AI moderated studies, intercept studies, and standalone screeners requires the MCP's newer drafting tools.

**If you can't draft these study types, your organization may not have approved the newer drafting tools yet.** Check with the team that manages AI tools at your organization.

In the meantime, you can keep building usability tests with the MCP's legacy drafting tools. For more information, see [Dscout MCP tools](https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-tools.md).

To build a study type the MCP doesn't support, such as a diary study or interview study, build it in Dscout.

</details>

<details>

<summary>Export can't be created</summary>

Some exports can only be created in Dscout, including PDF exports, crosstab exports, participant ZIP exports, single-transcript CSV files, and session and screen-share videos. If your AI tool says it can't create one of these exports, create it in Dscout instead.

To get a combined screen and camera video for one session, ask your AI tool to create one. It renders in the background, and you'll get an email when it's ready.

</details>

<details>

<summary>Video player or chart doesn't appear</summary>

The Dscout MCP's video player and question charts only appear in AI tools that support interactive views, such as Claude. If your AI tool doesn't show them, it will describe the results in text instead.

To watch a recording, clip, or highlight reel, ask your AI tool for a download link. To watch a full session, open it in Dscout.

</details>

<details>

<summary>Full session can't be played</summary>

Full-session playback is available for usability tests, AI moderated studies, and intercept studies. It isn't available for interview studies or diary studies.

Even in a supported study, a session can't play in your chat if:

* Any of its recordings are still processing.
* It’s made up of an unusually large number of separate recordings, which can happen if a participant’s screen share or camera stopped and restarted many times.

In these cases, watch the session in Dscout. If you'd like a single combined video file instead, ask your AI tool to create one. It renders in the background, and you'll get an email when it's ready.

If your AI tool says the session can't be played for another reason, watch it in Dscout.

</details>

<details>

<summary>Session link expired</summary>

The video player's links expire after 24 hours. If a session that played earlier no longer loads, ask your AI tool to show the session again.

</details>

### Learn more

Learn more about the Dscout MCP in these articles:

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td>Dscout MCP overview</td><td><a href="https://help.dscout.com/dscout-ai/dscout-mcp.md">Dscout MCP</a></td></tr><tr><td>Set up the Dscout MCP</td><td><a href="https://help.dscout.com/dscout-ai/dscout-mcp/set-up-the-dscout-mcp.md">Set up the Dscout MCP</a></td></tr><tr><td>MCP prompt library</td><td><a href="https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-prompt-library.md">Dscout MCP prompt library</a></td></tr><tr><td>MCP best practices</td><td><a href="https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-best-practices.md">Dscout MCP best practices</a></td></tr><tr><td>MCP tool breakdown</td><td><a href="https://help.dscout.com/dscout-ai/dscout-mcp/dscout-mcp-tools.md">Dscout MCP tools</a></td></tr></tbody></table>


---

# 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.dscout.com/dscout-ai/dscout-mcp/troubleshoot-the-dscout-mcp.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.
