Atlassian

Overview

The Atlassian server enables AI assistants to interact with Jira and Confluence, providing comprehensive project management and documentation capabilities through Rovo-powered intelligent search and full read/write access.

How to Add Atlassian

1. 1
   Access Atlassian Administration

   1. Go to Atlassian Administration and select your organization
   2. Navigate to Apps > AI settings > Rovo MCP server
2. 2
   Configure Domain Access

   1. Add or remove domains as needed for your organization
   2. You can use Atlassian's default supported domain list or specify your own
   3. These controls apply to OAuth connections only (API token connections aren't restricted)
3. 3
   Connect to Civic

   1. Add the Atlassian server to your Civic environment through the server directory
   2. Authorize using OAuth when prompted
4. 4
   Test Connection

   Start with a simple command like "Search Jira for all my open tasks" or "List my recent Confluence pages" to verify the connection works properly.

tip

For more details, see Control Atlassian Rovo MCP server settings

What You Can Do

Intelligent Search

Use Rovo Search to find content across Jira and Confluence with natural language queries

Project Management

Create, update, and transition Jira issues with full field management and workflow control

Documentation

Create and update Confluence pages with Markdown formatting and comment management

Cross-Product Workflows

Build workflows that span Jira and Confluence for seamless collaboration

Available Tools (28)

Search & Discovery

search

Rovo-powered intelligent search across both Jira and Confluence. Use this by default for natural language queries.

searchJiraIssuesUsingJql

Search Jira issues using JQL (Jira Query Language) for precise field-level filtering

searchConfluenceUsingCql

Search Confluence content using CQL (Confluence Query Language) for advanced queries

Jira Management

createJiraIssue

Create new Jira issues with custom fields, assignees, and metadata

getJiraIssue

Retrieve detailed information about a specific Jira issue

editJiraIssue

Update fields on existing Jira issues

transitionJiraIssue

Move issues through workflow states

addCommentToJiraIssue

Add comments to Jira issues with optional visibility restrictions

Confluence Management

createConfluencePage

Create new Confluence pages with Markdown content

updateConfluencePage

Update existing Confluence pages with version tracking

getConfluencePage

Retrieve page content converted to Markdown format

createConfluenceFooterComment

Add general comments to pages

createConfluenceInlineComment

Add comments attached to specific text selections

Use Cases

Sprint Planning

"Search Jira for all tasks in project AUTH with status 'Backlog' created in the last 2 weeks. Show me the top 10, then transition them to 'Selected for Development' and add a comment 'Added to Sprint 23'"

Team Standup Preparation

"Show me all Jira issues assigned to me that are 'In Progress'. For each issue, get the latest comments and summarize my current status. Also show which issues are due this week."

Documentation Sync

"Search for all bugs in project AUTH tagged 'api-endpoint' that were resolved this sprint. Create a Confluence page in the Labs space titled 'Sprint 23 - API Endpoints Completed' with a summary of each bug and its resolution."

Research Workflow

"Search for 'authentication analytics' across Jira and Confluence, summarize the top 5 results, then create a new Confluence page in the Labs space titled 'Authentication Analytics Research Summary' with your findings"

note

Available Products: Both Confluence and Jira with full read/write capabilities

Search Tip: Use Rovo Search (search) by default for intelligent cross-product search. Only use CQL/JQL when you need precise field-level filtering.

URL Handling: Most tools accept full Confluence/Jira URLs and will extract IDs automatically.

Content Format: All page and comment creation uses Markdown format.

warning

The MCP server currently requests over-privileged access, so you cannot limit it to read-only operations. Coupled with the lack of approval requests in Civic, care must be taken when using this MCP server.

---

Guardrails

In addition to the 14 universal guardrails, this server has 72 server-specific guardrails across 20 operations (Jira and Confluence combined).

note

Most comprehensive guardrail set on the platform — 72 specific guardrails across 20 operations spanning both Jira and Confluence. All require values configured before use (allowlists, blocklists, length limits, etc.).

Jira Guardrails

addCommentToJiraIssue

Guardrail	Timing	Description
Block Comments on Specific Issues	Request	Blocks comments on protected issue IDs/keys
Filter Comment Content	Request	Blocks comments containing sensitive keywords
Limit Comment Length	Request	Caps commentBody length
Prevent Visibility Restrictions	Request	Blocks setting commentVisibility

atlassianUserInfo

Guardrail	Timing	Description
Hide User Account IDs	Response	Redacts accountId from user info responses
Hide User Email Addresses	Response	Redacts email from user info responses

createJiraIssue

Guardrail	Timing	Description
Block Creation in Specific Projects	Request	Blocks issue creation in sensitive project_key values
Restrict Issue Types	Request	Allowlist for issueTypeName
Prevent Assignment to Specific Users	Request	Blocklist for assignee_account_id
Limit Additional Fields	Request	Allowlist for additional_fields usage

editJiraIssue

Guardrail	Timing	Description
Block Edits to Specific Issues	Request	Protects issue IDs/keys from modification
Prevent Field Modifications	Request	Blocks changes to specific field values
Filter Field Values	Request	Blocks sensitive data in field updates

getJiraIssue

Guardrail	Timing	Description
Block Access to Specific Issues	Request	Protects sensitive issues by ID/key
Hide Sensitive Issue Fields	Response	Redacts fields from issue responses
Redact User Information	Response	Redacts fields.assignee and other user data
Filter Issue History	Response	Redacts changelog from responses

getJiraIssueRemoteIssueLinks

Guardrail	Timing	Description
Hide Remote Links	Response	Redacts all external references (links[*])

getJiraProjectIssueTypesMetadata

Guardrail	Timing	Description
Block Access to Specific Projects	Request	Protects project metadata by ID/key
Hide Custom Issue Types	Response	Filters sensitive issueTypes[*] from responses

getVisibleJiraProjects

Guardrail	Timing	Description
Block Specific Actions	Request	Blocks certain actions (permission queries)
Limit Results	Request	Caps maxResults
Filter Project List	Response	Hides sensitive projects from listing
Hide Project Details	Response	Redacts project metadata

lookupJiraAccountId

Guardrail	Timing	Description
Block User Lookups	Request	Prevents email/name enumeration via searchString
Limit Search Scope	Request	Restricts searchString patterns
Hide User Details	Response	Redacts results[*] account information

searchJiraIssuesUsingJql

Guardrail	Timing	Description
Block Sensitive JQL Queries	Request	Blocks JQL for confidential issues
Block Project Searches	Request	Blocks JQL targeting specific projects
Limit Search Results	Request	Caps maxResults
Filter Search Results	Response	Hides sensitive issues[*] from results
Hide Issue Fields	Response	Redacts issues[*].fields from JQL results

transitionJiraIssue

Guardrail	Timing	Description
Block Specific Transitions	Request	Prevents certain transitionId values
Prevent Transitions on Protected Issues	Request	Blocks status changes by issueIdOrKey
Require Transition Comments	Request	Enforces fields.comment must exist

Confluence Guardrails

createConfluencePage

Guardrail	Timing	Description
Block Page Creation in Spaces	Request	Prevents page creation in sensitive spaceId values
Filter Page Creation Content	Request	Blocks pages with sensitive keywords in body
Limit Page Content Size	Request	Caps body length
Prevent Private Page Creation	Request	Blocks isPrivate = true

updateConfluencePage

Guardrail	Timing	Description
Block Updates to Pages	Request	Protects critical pages by pageId
Filter Update Content	Request	Blocks sensitive keywords in page body updates
Prevent Status Changes	Request	Blocks draft/current status transitions
Prevent Page Moves	Request	Blocks spaceId/parentId changes
Require Version Messages	Request	Enforces versionMessage must exist

getConfluencePage

Guardrail	Timing	Description
Block Specific Page IDs	Request	Protects sensitive pages by pageId
Filter Pages from Spaces	Request	Blocks access from sensitive spaceId values
Block Page on Sensitive Words	Response	Rejects entire page if sensitive keywords found in body

getPagesInConfluenceSpace

Guardrail	Timing	Description
Block Specific Space IDs	Request	Protects entire spaces by spaceId
Filter Deleted/Trashed Pages	Request	Blocks status values like deleted/trashed
Limit Pages Per Space Query	Request	Caps limit parameter
Hide Draft/Archived Pages	Response	Filters results[*].status
Redact Page Content	Response	Masks sensitive info in results[*].body

getConfluenceSpaces

Guardrail	Timing	Description
Block Specific Space Keys	Request	Denies access to sensitive spaces by keys
Limit Space Results Per Page	Request	Caps limit
Hide Archived Spaces	Response	Filters spaces by results[*].status
Hide Space Descriptions	Response	Redacts results[*].description

searchConfluenceUsingCql

Guardrail	Timing	Description
Block Sensitive CQL Queries	Request	Blocks CQL for passwords/secrets
Block CQL Wildcard Searches	Request	Prevents broad cql patterns
Limit CQL Search Results	Request	Caps limit
Filter CQL Search Results	Response	Hides sensitive pages from results[*]

createConfluenceFooterComment

Guardrail	Timing	Description
Block Footer Comment Creation	Request	Protects specific pages from footer comments
Filter Footer Comment Content	Request	Blocks sensitive keywords in body
Limit Footer Comment Length	Request	Caps body length

getConfluencePageFooterComments

Guardrail	Timing	Description
Block Footer Comments by Page	Request	Blocks access to footer comments by pageId
Hide Footer Commenter Info	Response	Redacts results[*].author
Redact Footer Comment Content	Response	Masks sensitive keywords in results[*].body

createConfluenceInlineComment

Guardrail	Timing	Description
Block Inline Comment Creation	Request	Protects sensitive pages from inline comments
Filter Inline Comment Content	Request	Blocks sensitive keywords in body
Prevent Comments on Text	Request	Blocks certain textSelection values

getConfluencePageInlineComments

Guardrail	Timing	Description
Filter Inline Comments by Status	Request	Blocks access to draft/other status comments
Redact Inline Comment Content	Response	Masks sensitive info in results[*].body

getAccessibleAtlassianResources

Guardrail	Timing	Description
Limit Accessible Resources	Response	Caps the number of Atlassian resources returned

tip

Configure guardrails via the Civic UI or ask the Configurator Agent: "Add guardrails to my Atlassian server."