Productivity

Atlassian

by Atlassian Pty Ltd

Overview

The Atlassian MCP Server connects ChatGPT and Codex to your Atlassian workspace, so you can work with Jira, Confluence, Bitbucket, Loom, and more directly from your conversation. Find and summarize Jira issues, create and update tickets, transition statuses, and add comments without switching tabs. Search, read, draft, and edit Confluence pages with full context. Supporting both read and write actions, the server lets you retrieve information and take action in real time. Dedicated UI components for Jira and Confluence bring issue details, page content, and updates right into ChatGPT, so you can review and act without leaving the conversation.

Tools

addCommentToJiraIssue

ChatGPT

Add comment

addGraphContext

ChatGPT

Adds a relationship between two entities in the Teamwork Graph (e.g. linking two Jira work items, marking one as blocking another, attaching a remote link, or connecting a Jira work item to an Atlas project or goal).

addOrEditJiraIssueComment

ChatGPT

Add a comment to a Jira issue, or edit an existing one: omit commentId to add, or pass one from listJiraIssueComments to edit. Returns the commentId, needed to edit or delete it later. When no file was appended through inlineFileId, it also returns the echoed body and its format (appliedContentFormat).

addWorklogToJiraIssue

ChatGPT

Add or update a worklog on a Jira issue. When worklogId is provided, updates that worklog;

atlassianHome

ChatGPT

Open Atlassian Home to see pull requests and recent work.

atlassianUserInfo

ChatGPT

Get current user info

createConfluenceContent

ChatGPT

Create a new Confluence page, blog post, live doc, whiteboard, database, embed, smart link, or folder. Before choosing body.format or authoring a body, call getContentFormatGuide through execute with name=getContentFormatGuide and inputs={toolName}. Use createConfluencePage for pages, blog posts, and live docs; createConfluenceWhiteboard for whiteboards; or createConfluenceDatabase for databases. Space instructions describe how to author content in a Confluence space. Apply relevant guidance to the content you create or update. Follow this decision rule: 1. Before authoring, call getConfluenceSpace for the target space unless getConfluenceContent returned metadata.hasSpaceInstructions=false for content in that space. If getConfluenceSpace already returned for the same cloudId and space during the current task, reuse its spaceInstructions and do not call it again. 2. When the value is true or unknown and instructions have not been loaded, you must call getConfluenceSpace once before authoring through execute with name=getConfluenceSpace, top-level cloudId, and inputs={spaceIdOrKey}. 3. Apply any returned spaceInstructions. If a successful response omits them, no instructions are configured; author with defaults and do not block. After a successful getConfluenceSpace call, do not make a separate getConfluenceSpaceInstructions call.

createConfluenceFooterComment

ChatGPT

Create footer comment

createConfluenceInlineComment

ChatGPT

Create inline comment on specific text

createConfluencePage

ChatGPT

Create Confluence page

createIssueLink

ChatGPT

Create a link between two Jira issues. If the user does not specify a link type, use getIssueLinkTypes to fetch available link types for the site.

createJiraIssue

ChatGPT

Create issue

discover

ChatGPT

Find Atlassian operations that are not already in your tool list. Searches ~310 operations across Jira, Confluence, Compass, Bitbucket, Focus, Goals, Projects, Loom, Talent, Teams, Capacity-planning, Jira Align, Artifacts. Returns up to 5 matches with the exact name and inputs needed to call the matching execute-family tool (executeRead, executeWrite, or executeDestructive), then a briefer name-and-summary list of further matches — re-query with narrower terms to get one of those in full. Read all 5 before choosing. Only use an operation name from discover results or one already in your tool list; never guess, assume, or invent a name — when unsure, call discover first.

editJiraIssue

ChatGPT

Update issue

executeDestructive

ChatGPT

Run a destructive Atlassian operation by name (deletes or irreversibly changes data) across all Atlassian products. Only use an operation name from discover results or one already in your tool list; never guess, assume, or invent a name — when unsure, call discover first. If the user provides a Jira/Confluence URL, pass it directly as cloudId — no need to call getAccessibleAtlassianResources. Pass all inputs as a flat object — the server routes each to the right location (path, query, or body) automatically. Use responseFields for field filtering, e.g. ["key","fields.summary","fields.status.name"]. Use view to select a named output preset (e.g. "compact", "evidence", "full") when the operation supports views.

executeRead

ChatGPT

Run a read-only Atlassian operation by name across all Atlassian products. Only use an operation name from discover results or one already in your tool list; never guess, assume, or invent a name — when unsure, call discover first. If the user provides a Jira/Confluence URL, pass it directly as cloudId — no need to call getAccessibleAtlassianResources. Pass all inputs as a flat object — the server routes each to the right location (path, query, or body) automatically. Use responseFields for field filtering, e.g. ["key","fields.summary","fields.status.name"]. Use view to select a named output preset (e.g. "compact", "evidence", "full") when the operation supports views.

executeWrite

ChatGPT

Run a write Atlassian operation by name (creates or updates data, non-destructive) across all Atlassian products. Only use an operation name from discover results or one already in your tool list; never guess, assume, or invent a name — when unsure, call discover first. If the user provides a Jira/Confluence URL, pass it directly as cloudId — no need to call getAccessibleAtlassianResources. Pass all inputs as a flat object — the server routes each to the right location (path, query, or body) automatically. Use responseFields for field filtering, e.g. ["key","fields.summary","fields.status.name"]. Use view to select a named output preset (e.g. "compact", "evidence", "full") when the operation supports views.

fetch

ChatGPT

Get details of a Jira issue or Confluence page by ARI (Atlassian Resource Identifier), if the id is not an ARI, then use a different tool to fetch the content

getAccessibleAtlassianResources

ChatGPT

Get cloudid to make tool calls

getCollaborators

ChatGPT

Find a person's strongest collaborators across Atlassian work, ranked by collaboration score. Omit accountId, name, and email to use the current user; otherwise supply accountId or resolve one person with name and/or email. Limit controls the number returned. Utilizing this tool may consume Rovo credits.

getConfluenceCommentChildren

ChatGPT

Get reply(child) comments for a comment

getConfluenceContent

ChatGPT

REQUIRED: Supply at least one content locator: content_id or content_url. Read any Confluence content (page, blog, live doc, comment, whiteboard, embed, database, folder).

getConfluencePage

ChatGPT

Get a Confluence page by page ID, including body content.

getConfluencePageDescendants

ChatGPT

Get child pages of specified page

getConfluencePageFooterComments

ChatGPT

Get page footer comments

getConfluencePageInlineComments

ChatGPT

Get page inline comments

getConfluenceSpaces

ChatGPT

Get spaces

getGraphContext

ChatGPT

Retrieves connected context from Teamwork Graph for any Atlassian entity. Returns all relationships and linked objects within one traversal – including cross-product and third-party connections. Use when the answer requires connections between entities, not just a single entity's fields. Supported entry points: Jira: issues, projects, sprints, versions, comments Confluence: pages, blogposts, whiteboards, databases, spaces Goals, Projects, Focus Areas, Tags and updates People: users, teams, organisations DevOps: PRs, repos, deployments, services, builds, designs Loom: videos, meetings Compass: components Assets: objects Incidents, conversations, calendar events, external documents After calling this tool, call getGraphObject on returned ARIs to get full content. The utilisation of this tool may consume up to 10 Rovo Credits. If the user or organization does not have any Rovo Credits available, the tool call will fail.

getGraphObject

ChatGPT

Fetches the entire available data for one or more objects (Atlassian or third-party) using their ARIs or URLs. Use for the objects gathered from getGraphContext tool.

getIssueLinkTypes

ChatGPT

Get available Jira issue link types (e.g. Duplicate, Blocks, Clones, Relates).

getJiraIssue

ChatGPT

Get issue details

getJiraIssueRemoteIssueLinks

ChatGPT

Get remote links

getJiraIssueTypeMetaWithFields

ChatGPT

Get field metadata

getJiraProjectIssueTypesMetadata

ChatGPT

Get issue types

getLoomVideo

ChatGPT

Reads a Loom video's core metadata and optionally its transcript, comments, AI agent briefs, AI-extracted meeting action items, or attached links in one call via the expand input. USE WHEN the user asks about a specific Loom video — its title, description, duration, owner, view/comment/reaction counts, what was said in it (pass expand: ["transcript"]), what feedback or comments people left on it (pass expand: ["comments"]), what the AI summarised as key points (pass expand: ["agentBriefs"]), or what follow-up tasks or action items the AI extracted from a meeting recording (pass expand: ["meetingActionItems"]), or which links are attached to it (pass expand: ["links"]). DO NOT USE to get the downloadable MP4 file — use getLoomVideoDownloadUrl for that. To find a video's ARI first, use listLoomVideos or listLoomVideosSharedWithMe.

getPagesInConfluenceSpace

ChatGPT

Get pages in space

getPeopleInfo

ChatGPT

Get people’s profiles and optional immediate reporting relationships. Provide cloudId and exactly one selector: identifier (an array of 1–10 Atlassian account IDs or IdentityUser ARIs), name, or email. Name and email each resolve one person; use name: "me" for yourself. If a name is ambiguous, use the returned candidates to disambiguate with an account ID or exact email; do not guess. The profile is always requested. Set manager: true, directReports: true, or both in one call. Results contain identity and requested reporting facets, each with a status. Use successful results when others fail; partial or unavailable data does not establish that a relationship is absent. Reporting relationships do not establish expertise, ownership, or delivery responsibility. Utilizing this tool may consume Rovo credits.

getTransitionsForJiraIssue

ChatGPT

Get transitions

getVisibleJiraProjects

ChatGPT

Get projects

getWorkActivity

ChatGPT

Get authored or explicitly selected work activity for the current user, up to 10 people by identifiers, or one person by name or exact email. Defaults to the last seven days with counts and up to five summary items per section. Filter using activity, types, and time bounds; countsOnly omits previews. Utilizing this tool may consume Rovo credits.

getWorkPortfolio

ChatGPT

Returns native and inferred projects, owned goals, and focus areas for up to 10 root identifiers per call, including their immediate reports by default. Includes project ownership and contribution relationships, status, and updates. Utilizing this tool may consume Rovo credits.

lookupJiraAccountId

ChatGPT

Lookup user IDs

search

ChatGPT

Search Jira and Confluence using Rovo Search, ALWAYS use this tool to search for Jira and Confluence content unless the word CQL or JQL is used in the context

searchConfluence

ChatGPT

Search Confluence content with CQL

searchConfluenceUsingCql

ChatGPT

Search content with CQL

searchJiraIssuesUsingJql

ChatGPT

Search issues with JQL

search_mentions

ChatGPT

Search Jira and Confluence content, people, and teams to reference in a message. Called by the host composer when the user types an at-mention; not for model use.

transitionJiraIssue

ChatGPT

Transition issue status

updateConfluenceContent

ChatGPT

Update Confluence docs, whiteboards, or databases. Before choosing body.format or authoring an edit, call getContentFormatGuide through execute with name=getContentFormatGuide and inputs={toolName}. Use updateConfluencePage for pages, blog posts, and live docs; updateConfluenceWhiteboard for whiteboards; or updateConfluenceDatabase for databases. Space instructions describe how to author content in a Confluence space. Apply relevant guidance to the content you create or update. Follow this decision rule: 1. Before authoring, call getConfluenceSpace for the target space unless getConfluenceContent returned metadata.hasSpaceInstructions=false for content in that space. If getConfluenceSpace already returned for the same cloudId and space during the current task, reuse its spaceInstructions and do not call it again. 2. When the value is true or unknown and instructions have not been loaded, you must call getConfluenceSpace once before authoring through execute with name=getConfluenceSpace, top-level cloudId, and inputs={spaceIdOrKey}. 3. Apply any returned spaceInstructions. If a successful response omits them, no instructions are configured; author with defaults and do not block. After a successful getConfluenceSpace call, do not make a separate getConfluenceSpaceInstructions call.

updateConfluencePage

ChatGPT

Update Confluence page

Atlassian tools

Claude

Atlassian’s Rovo MCP Server enables secure, permission-aware access to Jira and Confluence from external AI tools like Claude. It supports summarization, creation, and multi-step actions, helping teams tap into structured enterprise knowledge wherever they work—all while preserving data privacy and leveraging Atlassian’s open, interoperable Teamwork Graph foundation.

addCommentToJiraIssue

Claude

addOrEditJiraIssueComment

Claude

addTeamworkGraphContext

Claude

atlassianUserInfo

Claude

createCompassComponent

Claude

createCompassComponentRelationship

Claude

createCompassCustomFieldDefinition

Claude

createConfluenceContent

Claude

createConfluenceFooterComment

Claude

createConfluenceInlineComment

Claude

createConfluencePage

Claude

createJiraIssue

Claude

discover

Claude

editJiraIssue

Claude

executeDestructive

Claude

executeRead

Claude

executeWrite

Claude

getAccessibleAtlassianResources

Claude

getCompassComponent

Claude

getCompassComponents

Claude

getCompassCustomFieldDefinitions

Claude

getConfluenceContent

Claude

getConfluencePage

Claude

getConfluencePageAncestors

Claude

getConfluencePageDescendants

Claude

getConfluencePageFooterComments

Claude

getConfluencePageInlineComments

Claude

getConfluenceSpaces

Claude

getJiraIssue

Claude

getJiraIssueRemoteIssueLinks

Claude

getJiraProjectIssueTypesMetadataZapier

Claude

getLoomVideo

Claude

getPagesInConfluenceSpace

Claude

getTeamworkGraphContext

Claude

getTeamworkGraphObject

Claude

getTransitionsForJiraIssue

Claude

getVisibleJiraProjects

Claude

lookupJiraAccountId

Claude

search

Claude

searchConfluence

Claude

searchConfluenceUsingCql

Claude

searchJiraIssuesUsingJql

Claude

transitionJiraIssue

Claude

updateConfluenceContent

Claude

updateConfluencePage

Claude

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Links

Documentation ↗Privacy Policy ↗

App Stats

Tools

Prompts

ChatGPT, Claude

Platforms