> For the complete documentation index, see [llms.txt](https://docs.storylane.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.storylane.io/mcp/storylane-mcp/security-permissions-troubleshooting.md).

# Security, Permissions, Troubleshooting

How access works, what data leaves Storylane, and fixes for common errors.

## Security, permissions and troubleshooting

#### How access works

MCP uses OAuth. Your AI client never receives your Storylane password. Agents reach only the workspace data your own permissions allow, so an MCP connection cannot widen what you can see.

Revoke access at any time from **Settings → Connectors** in your AI client, or regenerate M2M credentials from **Settings → Integrations → MCP**.

#### What leaves Storylane

Tool responses pass through whichever AI client you connect, and are stored in that client's conversation history under its own retention policy.

{% hint style="info" %}
Some tools return personal data. `list_leads`, `list_accounts`, `repx_get_analytics`, and `repx_list_leads` can include names, email addresses, IP addresses, company records, and CRM contact IDs. If your organisation restricts where customer data may be processed, review that before enabling these tools, and prefer the aggregate tools, `get_demo_analytics` and `repx_get_stats`, where they answer the question.
{% endhint %}

#### Workspace scoping

Operations run against the active workspace. Use `switch_workspace` when you have access to several. M2M credentials are locked to one workspace and cannot switch.

#### What MCP cannot do

* Capture a demo. Recording happens in the Chrome extension or desktop app.
* Edit screens, HTML, or individual guide text on an existing step.
* Reorder or delete steps or demos.
* Upload media as an asset.
* Create or configure RepX agents, Playbooks, or guardrails.
* Reply to a live buyer conversation.

#### Common problems

| Symptom                                   | Cause and fix                                                            |
| ----------------------------------------- | ------------------------------------------------------------------------ |
| Tools appear but every call fails         | MCP not on your plan. Check Settings to Integrations to MCP              |
| Deals tools error                         | No connected CRM, or Deals not enabled for the workspace                 |
| Alerts tools error                        | Alerts not enabled, or you are on the free plan                          |
| `create_hub` errors                       | Hubs not enabled for the workspace                                       |
| Personalized demo has no link             | It is still a draft. Run `publish_demo`                                  |
| Personalized demo has the wrong CTA       | Copies inherit the base demo's CTA. Set it explicitly with `update_demo` |
| A demo appears empty right after creation | Still processing. Poll `get_demo_status`                                 |
| Lead counts look low                      | Leads only exist where a demo or link is gated                           |
| Write actions fail in ChatGPT             | Developer Mode is off                                                    |
| Responses get truncated or slow           | Narrow the query. See Limits and processing times                        |

#### Getting help

If a tool returns an error you cannot place, include the tool name and the exact message when you contact support. Both appear in your AI client's tool call output.


---

# 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://docs.storylane.io/mcp/storylane-mcp/security-permissions-troubleshooting.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.
