Getting started with the Atlassian Remote MCP Server

What is the Remote MCP Server?

The Remote MCP Server is a cloud-based bridge between your Atlassian Cloud site and compatible external tools. Once configured, it enables those tools to interact with Jira and Confluence data in real-time. This functionality is powered by secure OAuth 2.1 authorization, which ensures all actions respect the user’s existing access controls.

Why use the Remote MCP Server?

The Remote MCP Server helps bring Atlassian data into your existing workflows:

• Summarize and search Jira and Confluence content without switching tools.

• Create and update issues or pages based on natural language commands.

• Bulk process tasks like generating tickets from meeting notes or specs.

It’s designed to support developers, content creators, and project managers working within IDEs or AI platforms.

Who is it for?

This tool is aimed at a range of users looking to integrate Atlassian functionality into their daily workflows without switching context:

• Developers and designers working primarily in IDEs.

• Teams using AI copilots (for example, Claude, Cursor) for increased productivity.

• Users aiming to automate Jira or Confluence tasks using natural language.

Supported clients

The following tools are currently supported with the Atlassian Remote MCP Server:

• Claude – Conversational AI by Anthropic with integration support for Claude Desktop and Claude for Teams.
  Visit Claude

• Cursor – An AI-first code editor designed for pair programming.
  Visit Cursor

• VS Code – Popular open-source IDE, compatible via the mcp-remote CLI.
  Visit Visual Studio Code

• Zapier – Automation tool for workflows that include Jira or Confluence triggers/actions.
  Visit Zapier

• HubSpot – CRM platform with AI and automation features.
  Visit HubSpot

In addition to the tools listed, we also support any local MCP-compatible client that can run on localhost and connect to the server via the mcp-remote proxy. This enables custom or third-party integrations that follow the MCP specification.

Before you start

Ensure your environment meets the necessary requirements to successfully set up the Remote MCP Server. This section outlines the technical prerequisites, access considerations, and security details.

Prerequisites

Before connecting to the Remote MCP Server, review the setup requirements for your environment:

For Claude (Cloud-based Setup)

• An Atlassian Cloud site with Jira and/or Confluence

• Access to Claude for Teams

• A modern browser to complete the OAuth 2.0 authorization flow

For IDEs or Local Clients (Desktop Setup)

• An Atlassian Cloud site with Jira and/or Confluence

• A supported IDE (for example, Claude desktop, VS Code, or Cursor) or a custom MCP-compatible client

• Node.js v18+ installed to run the local MCP proxy (mcp-remote)

• A modern browser for completing the OAuth login

Beta access and limits

The beta is open to all Atlassian Cloud customers. No special sign-up is required. However, usage is subject to rate limits:

• Standard plan: Moderate usage thresholds.

• Premium/Enterprise plans: Higher usage quotas (1,000 requests/hour plus per-user limits).

Data and security

Security is a core focus of the Remote MCP Server:

• All traffic is encrypted via HTTPS using TLS 1.2 or later.

• OAuth 2.0 ensures secure authentication and access control.

• Data access respects Jira and Confluence user permissions.

Choose your setup path

Depending on the tool you're using, the setup process may vary. Use the links below to jump to specific setup instructions:

• Setting up Claude.ai

• Setting up IDEs (like VS Code or Cursor)

• Understanding Authentication & OAuth

• Troubleshooting and verifying your setup

How It Works

Architecture and Communication

1. A supported client connects to the server endpoint:

   https://mcp.atlassian.com/v1/sse

2. A secure browser-based OAuth 2.0 flow is triggered.

3. Once authorized, the client streams contextual data and receives real-time responses from Jira or Confluence.

Permission Management

Access is granted only to data that the user already has permission to view in Atlassian Cloud. All actions respect existing project or space-level roles. OAuth tokens are scoped and session-based.

Example Workflows

Once connected, you can perform a variety of useful tasks from within your supported client.

Jira workflows

Use these examples to understand how to interact with Jira:

• Search: “Find all open bugs in Project Alpha.”

• Create/update: “Create a story titled ‘Redesign onboarding’.”

• Bulk create: “Make five Jira issues from these notes.”

Confluence workflows

Access and manage documentation content directly:

• Summarize: “Summarize the Q2 planning page.”

• Create: “Create a page titled ‘Team Goals Q3’.”

• Navigate: “What spaces do I have access to?”

Combined Tasks

Integrate actions across Jira and Confluence:

• Link content: “Link these three Jira tickets to the ‘Release Plan’ page.”

Note: Actual capabilities vary depending on your permission level and client platform.

Known limitations (Beta)

While the Remote MCP Server provides powerful integration capabilities, please be aware of the following limitations during the beta period:

• Bulk operations may be constrained by rate limits or may not support all input formats.

• Custom Jira fields may not be recognized or returned without explicit setup.

• Some clients like GitHub Copilot and Cursor may require custom configuration or are not fully supported.

• Workspace or site switching is not currently available within a single session.

Refer to the Atlassian Community for an up-to-date list of known issues and active development items.

Admin notes: Managing access

If you're an admin preparing your team to use the Remote MCP Server, keep the following considerations in mind:

• Ensure users have product access to Jira and/or Confluence via Atlassian Admin.

• Authorization tokens are tied to the user’s current product permissions—check these if data isn’t accessible.

• App authorizations can be revoked by end users through their profile settings or by admins in the Connect apps section of Atlassian Admin for site-level control.

• Consider establishing usage guidelines or policies for teams leveraging AI-driven content generation.

• Reach out to your Atlassian account representative for advice on OAuth scope control and long-term support planning.

Support and feedback

Your feedback plays a crucial role in shaping the Remote MCP Server. If you encounter bugs, limitations, or have suggestions:

• Visit the Atlassian Support Portal to report issues.

• Share your experiences and feature requests on the Atlassian Community.

• Enterprise customers can contact their Atlassian Customer Success Manager for advanced support and roadmap discussions.

We’re excited to collaborate with you to improve this capability before its general availability.