Rovo Fails When Following Linked Confluence Pages from Jira

[Carol Pretorius]

Hi everyone,

I'm seeing an issue with Rovo when working across Jira and Confluence.

When I'm in Jira, Rovo can successfully:

• Read the Jira issue
• Read issue details
• Retrieve linked Confluence pages

However, when Rovo attempts to open and read the linked Confluence page, it fails and never returns the page content.

The page:

• Exists
• Is accessible to users
• Has no page restrictions

Rovo reports

"status": 404,

"error": "The requested resource could not be found."

After this, Rovo enters a loop investigating tools and schemas instead of returning a result.

Has anyone successfully got Rovo to:

1. Read a Jira issue
2. Follow the linked Confluence page
3. Use content from both Jira and Confluence in the same response?

Or is this a known limitation/issue with cross-product retrieval?

Thanks

[Sami Shaik]

Hello @Carol Pretorius , 

@Mia Tamm _Simpleasyty_ isolation is the right one, and your answer to it (Rovo in Confluence reads the page, Rovo in Jira resolves the link but fails on the content) points at a specific layer that "the page is unrestricted" does not cover, because it sits above page permissions.

The first thing to check: a data security policy with an AI control on that space. In Atlassian Administration, Security, then Data protection, then Data security policies, a policy can carry controls that block Rovo or AI features from reading content in specific spaces, with per-space overrides. Atlassian's own KB describes the exact symptom you have: the space is visible and the page resolves, but the content cannot be read by the AI path, while a user (and Rovo inside Confluence itself) reads it fine (Unable to read Confluence pages within Rovo but can view spaces). The KB is written for the MCP path, but the policy applies to any cross-product read. Ask your org admin to open each policy, look at Overrides on the controls, and see whether that space is listed. If it is, that is your cause, and the test is adding a throwaway space to the same override and repeating the Jira read.

If no policy names the space, two more layers, one test each:

1. Which site the Confluence page lives on. Rovo in Jira reads Confluence content through the org's Rovo context, and if your organisation runs more than one site, a page on a different site than the Jira instance is a different case from a same-site page. Test: link a page from a space on the same site as the Jira space, and one from another site if you have it; if only the cross-site one fails, you have the answer.
2. Rovo access per app (Manage Rovo access). Blocking Rovo for one Jira-family app leaves Search and Chat available as long as any Jira app on the site still has Rovo, so a partial block can leave Chat working with a narrower reach than expected. Test: a fresh page in a fresh space, read from Jira, with the admin confirming Rovo is enabled for both Jira and Confluence on that site.

One last thing worth writing in the eventual support ticket, if it comes to that: the exact wording Rovo returns when it fails ("I don't have access," "I couldn't retrieve," or a generic error) tells support which layer refused, and they will ask for it first.

[Carol Pretorius]

hi @Mia Tamm _Simpleasyty_ yes Rovo in Confluence fine, this happens from Rovo in Jira trying to read content on an unrestricted Confluence page.

[Mia Tamm _Simpleasyty_]

Hi @Carol Pretorius interesting that Rovo can resolve the linked Confluence page but fails only when it tries to read the content.

I’d test the same page directly from Rovo in Confluence, then repeat with a brand-new unrestricted page in the same space. If both work directly but fail only when Rovo follows the Jira → Confluence link, you’ve got a much cleaner reproduction of a cross-product retrieval issue rather than a page permission problem.

[Carol Pretorius]

Hi @Mia Tamm _Simpleasyty_ yes Rovo in Confluence fine, this happens from Rovo in Jira trying to read content on an unrestricted Confluence page.