What your AI apps can do with Atlassian
- Find Jira issues
- Search Confluence content
Atlassian MCP tools
26 tools, taken from the publisher's documentation on 29 October 2026. The server decides what it offers and can add or rename tools at any time; after you connect, Toolstile shows the current list.
| Tool | What it does |
|---|---|
search | Rovo natural-language search across Jira, Confluence and connected apps (beta) |
searchJiraIssuesUsingJql | Searches Jira work items with JQL |
getJiraIssue | Reads one Jira work item |
listJiraIssueComments | Reads comments on a work item |
getJiraBoardSprintData | Reads a board and its active sprint |
createJiraIssue | Creates a work item |
editJiraIssue | Edits a work item's fields |
transitionJiraIssue | Changes status or moves an item to a sprint or backlog |
addOrEditJiraIssueComment | Adds or edits a comment |
manageJiraSprint | Creates, starts, updates or closes a sprint |
deleteJiraIssue | Permanently deletes a work item |
searchConfluence | Searches Confluence with CQL |
getConfluenceContent | Reads a page, blog post or other content |
diffConfluenceContentVersions | Diffs two versions of a page |
createConfluenceContent | Creates a page or other content |
updateConfluenceContent | Replaces or edits existing content |
moveConfluenceContent | Moves or archives content |
archiveConfluenceContent | Moves or archives content |
replaceConfluenceContentPermissions | Replaces all permission grants on content |
enableConfluencePublicLink | Turns on anonymous sharing for a page |
getTeamworkGraphContext | Follows links between Jira, Confluence and third-party objects |
getBitbucketRepoPullRequestDiff | Reads a Bitbucket pull request diff |
createBitbucketRepoPullRequest | Opens a Bitbucket pull request |
mergeBitbucketRepoPullRequest | Merges a Bitbucket pull request |
runBitbucketRepoPipeline | Triggers a Bitbucket pipeline |
executeDestructive | Runs any discovered destructive tool |
Suggested starting access
Toolstile read each Atlassian tool's description and wrote these starting selections by hand. They are a suggestion reviewed by Toolstile, not a guarantee: Atlassian decides what each tool does and can change it, so check that a selection fits each app before you save it.
Read Jira and Confluence
Read Jira work items, comments and sprints, and Confluence pages and page versions, by key or ID. JQL and CQL searches wait for approval. Nothing that changes content.
- Allow:
getJiraIssue,listJiraIssueComments,getJiraBoardSprintData,getConfluenceContent,diffConfluenceContentVersions - Require approval:
searchJiraIssuesUsingJql,searchConfluence
Update Jira work items with approval
Read Jira work items, comments and sprints by key or ID, plus creating and editing work items, changing their status and commenting. JQL searches and every change wait for approval. No deletions.
- Allow:
getJiraIssue,listJiraIssueComments,getJiraBoardSprintData - Require approval:
createJiraIssue,editJiraIssue,transitionJiraIssue,addOrEditJiraIssueComment,searchJiraIssuesUsingJql
In the access editor, choosing a suggestion adds the listed tools this server offers to your draft. Existing access stays as it is, blocks and approval requirements stay in force, and the suggestion doesn't grant tool names the server adds later. Nothing is saved until you choose Save changes.
Suggested access for each AI app
The documentation this list comes from doesn't mark Atlassian's tools as read-only or destructive. Read each tool's description and decide per app before allowing it.
Coding agent in Claude Code or Cursor. Allow the read tools so the agent can look things up without stopping, and require approval for tools that change shared data.
Chat or research app in Claude Desktop. Allow reading and searching. Allow writes only where you want the app to act for you.
Unattended agent, such as a scheduled Codex job. No one is watching the session, so keep it narrow: allow what the job needs, require approval for changes and block the rest.
Blocked tools are removed from the tool list an app sees, so it won't try them. Because rules apply per app, the same Atlassian connection can be broad in one app and read-only in another, and the credential stays in Toolstile instead of each app's config file.
How it works with Toolstile
- Connect once. Add Atlassian to a workspace (browser sign-in). Toolstile keeps the credential, so no agent config holds it.
- Choose access per app. Give Claude Code every Atlassian tool, give Cursor only the read tools, or keep Atlassian away from an app entirely.
- Share approved accounts. Teammates use the connection without copying tokens, and you can remove access in one place.
- Review activity. See which app called which tool and when, so you can tighten access with evidence.
Add the Atlassian MCP server to an AI app
Through Toolstile, every AI app uses one gateway entry, whichever servers you connect. In Claude Code:
claude mcp add --transport http toolstile 'https://toolstile.com/mcp'Then connect Atlassian in your workspace and choose which of its tools that app may use. Client setup covers Codex, Cursor and Claude Desktop.
To connect directly instead, add the Atlassian endpoint to each app separately. In Claude Code:
claude mcp add --transport http atlassian 'https://mcp.atlassian.com/v2/mcp'In Cursor's mcp.json:
{
"mcpServers": {
"atlassian": {
"url": "https://mcp.atlassian.com/v2/mcp"
}
}
}Some servers accept only clients they have approved, or need a token header. Check the Atlassian MCP documentation for what your client needs.
Before you connect
An Atlassian Cloud account. Your organization's app-access policies apply.
Server details
| Detail | Value |
|---|---|
| Publisher | Atlassian |
| Endpoint | https://mcp.atlassian.com/v2/mcp |
| Authentication | Browser sign-in |
| Categories | Development, Productivity, Sales & support |
| Tool list | 26 tools, observed 29 October 2026 (docs) |