Read and write Jira, Confluence, Bitbucket, JSM and Compass from your AI client — with your own permissions.
Atlassian's official cloud-hosted Rovo MCP server connects Jira, Confluence, Jira Service Management, Bitbucket and Compass to AI clients via OAuth 2.1. Exposed over MCP by the atlassian rovo mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Atlassian's official cloud-hosted Rovo MCP server connects Jira, Confluence, Jira Service Management, Bitbucket and Compass to AI clients via OAuth 2.1.
Everything the assistant can do here goes through one of these:
atlassianUserInfo — Return details about the currently authenticated Atlassian usergetAccessibleAtlassianResources — List the cloudId values you can reach; required before any other call because every tool needs a cloudIdgetJiraIssue — Fetch a single Jira issue by key or idcreateJiraIssue — Create a Jira issue in a given project and issue typeeditJiraIssue — Update fields on an existing Jira issuetransitionJiraIssue — Move a Jira issue through a workflow transitionaddCommentToJiraIssue — Post a comment on a Jira issueaddWorklogToJiraIssue — Log time against a Jira issuesearchJiraIssuesUsingJql — Run a JQL query and return matching issuesgetVisibleJiraProjects — List Jira projects the authenticated user can seegetTransitionsForJiraIssue — List workflow transitions available on an issuegetConfluencePage — Retrieve a Confluence page and its contentAn Atlassian Cloud site with at least one supported product. Local clients need Node.js 18+ to run the mcp-remote proxy, and a browser for the OAuth 2.1 flow (or an admin-enabled API token for headless setups).
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Atlassian Rovo's toolset — atlassianUserInfo, getAccessibleAtlassianResources, getJiraIssue and 19 more — is a fair guide to whether it matches your workflow. It is maintained by Atlassian rather than a third party, which usually means auth handling and breaking changes are dealt with faster.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
Paste raw notes and have the assistant create the five Jira issues that fall out of them, in the right project, with sensible summaries and descriptions.
From your IDE, ask what the acceptance criteria on the ticket you are implementing actually say, and log work against it without leaving the editor.
Run a JQL search for open bugs in a project, or read JSM alerts, and get a written status digest instead of scanning boards.
Create a Compass component from the current repository and query what depends on a service before you plan a breaking change.
| Tool | What it does |
|---|---|
| atlassianUserInfo | Return details about the currently authenticated Atlassian user. |
| getAccessibleAtlassianResources | List the cloudId values you can reach; required before any other call because every tool needs a cloudId. |
| getJiraIssue | Fetch a single Jira issue by key or id. |
| createJiraIssue | Create a Jira issue in a given project and issue type. |
| editJiraIssue | Update fields on an existing Jira issue. |
| transitionJiraIssue | Move a Jira issue through a workflow transition. |
| addCommentToJiraIssue | Post a comment on a Jira issue. |
| addWorklogToJiraIssue | Log time against a Jira issue. |
| searchJiraIssuesUsingJql | Run a JQL query and return matching issues. |
| getVisibleJiraProjects | List Jira projects the authenticated user can see. |
| getTransitionsForJiraIssue | List workflow transitions available on an issue. |
| getConfluencePage | Retrieve a Confluence page and its content. |
| createConfluencePage | Create a new Confluence page in a space. |
| updateConfluencePage | Update the body or title of an existing Confluence page. |
| getConfluenceSpaces | List Confluence spaces available to the user. |
| getPagesInConfluenceSpace | List the pages contained in a Confluence space. |
| searchConfluenceUsingCql | Search Confluence content with a CQL query. |
| createConfluenceFooterComment | Add a footer comment to a Confluence page. |
| getJsmOpsAlerts | Read Jira Service Management Operations alerts (API-token auth only). |
| updateJsmOpsAlert | Update a Jira Service Management Operations alert (API-token auth only). |
| getTeamworkGraphContext | Aggregate contextual information across Atlassian products and connected apps. |
| getTeamworkGraphObject | Fetch a specific object from the Atlassian Teamwork Graph. |
claude mcp add atlassian https://mcp.atlassian.com/v1/mcp/authv2 -t httpAn Atlassian Cloud site with at least one supported product. Local clients need Node.js 18+ to run the mcp-remote proxy, and a browser for the OAuth 2.1 flow (or an admin-enabled API token for headless setups).
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.