Blank white background with no objects or features visible.

「Gartner Hype Cycle for AI Governance 2026」の全編を無料で公開しています。レポートを入手する →

Atlassian MCPサーバー:セットアップ、許可リスト、安全なアクセス

By アシシュ・ドゥベイ

Updated: October 7, 2026

Published: September 16, 2026

⚡ TL;DR

Fine-tuning vs prompting is the wrong debate for most product teams. The useful fork is Learn / Ground / Specialize: prove the workflow with a prompted model, ground answers in your docs when knowledge is the job, and only then specialize a small model on a narrow slice once labels, an owner, and volume exist.

PMs keep getting pulled into the same meeting. Someone says "we should fine-tune." Someone else says "just use GPT." Security asks where the prompts go. Eng asks who will own the model after launch. Nobody shares a checklist, so the room picks a model brand instead of a strategy.

We saw this pattern enough times that we stopped treating fine-tuning vs prompting as a bake-off. Those are tools. The product decision is which track you are on this quarter, and what has to be true before you move.

If you own the roadmap (not just the model pick), this is the frame we wish we had earlier: what people mix up, which gates actually matter, and how to brief eng and security without starting a training project by accident.

What the Atlassian MCP server is

The Atlassian MCP server is Atlassian’s Rovo MCP server: a remote Model Context Protocol endpoint that exposes Jira, Confluence, and Compass as tools an AI agent can call. It lives at https://mcp.atlassian.com/v1/mcp and authenticates over OAuth2.

It spans three products:

Product What agents can do
Jira Search issues, read issue detail, create tickets
Confluence Read pages and search content
Compass Work with component and service catalogue data
Cross-product Chain work across all three in one session

The docs describe the surface in terms of searching issues, reading pages, and creating tickets rather than naming tool functions. The authoritative list is whatever appears on the Tools tab after you authorize, since the gateway reflects the live upstream list.

Because it is remote, there is nothing to run locally — no Docker container, no npx process per laptop. You point an MCP client at a URL and authenticate, which is the appeal of remote MCP servers generally.

What agents actually do with it

The interesting uses chain tools across products:

  • Sprint triage. Search open Jira issues, cluster near-duplicates, pull each cluster’s linked Confluence spec to check whether the requirement changed, and create a consolidated ticket.
  • Incident writeup. Read the Jira incident, search Confluence for the runbook, pull the owning service from Compass, and draft a postmortem citing all three.
  • Spec-to-ticket. Read a Confluence spec, break it into Jira tickets with acceptance criteria lifted from the page, and link each back to the source.
  • Ownership lookup. A question arrives about a service nobody recognizes. The agent queries Compass for the component, then answers from its Confluence architecture page.

The split that matters is not just read versus write — it’s public versus sensitive. Reading a Jira issue is harmless. Creating one is recoverable. Reading Confluence deserves the most thought: it’s where companies put board decks, compensation bands, postmortems naming individuals, and security architecture. A read-only agent with unrestricted Confluence access has a wider blast radius than a write-capable agent limited to one Jira project.

That asymmetry is specific to Atlassian, and it’s why “disable the write tools” is incomplete advice here.

Why connecting it raw breaks at team scale

One engineer wiring this into Cursor is fine. Thirty engineers plus a support agent and a docs agent is a different problem.

The allowlist is an org-wide decision. It is set per organization, not per team. Whoever holds org admin in admin.atlassian.com decides whether this integration exists at all. Connect tooling ad hoc and you accumulate allowed domains nobody reviews.

No audit trail of intent. Atlassian logs that an API call happened against a user’s account. It does not log that your triage agent made it while acting on a prompt from a Slack thread. When a ticket appears nobody remembers filing, there’s no chain to reconstruct.

Confluence read scope is “everything the user can see.” Per-user permissions are the right design, but most tenants have permissive Confluence space permissions by historical accident. What a user can see is usually far more than what a task needs, and the agent cannot tell the difference.

Prompt injection has somewhere to land. Jira descriptions and Confluence pages are text an agent reads and someone else may have written. An issue filed by an external reporter through a service desk portal, containing instructions, read during triage with Confluence access live in the same session — that’s a path from untrusted input to sensitive output. The failure isn’t that the agent misbehaved; it’s that its permissions were wider than its task.

None of these are reasons to avoid the server. They’re reasons to put a control plane in front of it — which is what an MCP gateway is for.

Try it yourself.
Spin up a TrueFoundry account, allowlist your domain in Atlassian once, and give your team governed Jira and Confluence access.

Step 0: allowlist TrueFoundry in Atlassian

This is the step that blocks teams, so it goes first. It is an Atlassian-side prerequisite and no TrueFoundry setting substitutes for it.

You need: permission to add MCP servers in TrueFoundry, an Atlassian Cloud org with Jira, Confluence, or Compass, and organization admin access in admin.atlassian.com.

In Atlassian Admin, select your organization and open Apps → AI settings → Rovo MCP server. Under Allowed domains, add your TrueFoundry control plane domain:

https://<tfy-control-plane-base-url>/**

There is no OAuth client to create. Atlassian handles dynamic client registration for allowlisted domains. For most self-registered remote MCP servers you’d create an OAuth app in the provider’s portal, set a redirect URI, and store a client ID and secret. Here you don’t — the allowlist entry is the trust relationship.

The allowlist is your kill switch. Removing the domain revokes new OAuth connections. Stopping this integration org-wide is one change in Atlassian Admin, independent of the gateway. Few integrations give you a control that clean; write down where it lives.

One networking caveat: if Atlassian IP allowlisting is enabled, also allow traffic from the environment where TrueFoundry connects to the remote MCP server.

Connecting the Atlassian MCP server through TrueFoundry

Step 1 — Open the picker. In TrueFoundry, open MCP Gateway, click Add MCP Server, and select Atlassian.

Add MCP Server picker showing the available registration paths including official remote servers, any remote MCP server, TrueFoundry Managed MCPs, Hosted STDIO, and Import from OpenAPI Spec

Add MCP Server picker showing the available registration paths including official remote servers, any remote MCP server, TrueFoundry Managed MCPs, Hosted STDIO, and Import from OpenAPI Spec

This is not the TrueFoundry Managed MCP catalogue flow, where you supply only a name and the platform owns every field. Atlassian takes explicit values, because the trust relationship came from the allowlist rather than from platform-held credentials.

Step 2 — Configure the server. Use these values:

Field

Value

Name

atlassian

Description

Atlassian is a software development platform

URL

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

Authentication

OAuth2

Turn on Auth Data and select the OAuth2 tab. Because your domain is allowlisted, you do not need a client ID or secret — leave them empty.

Step 3 — Add collaborators. Add the users or teams that should use Atlassian tools. Assign MCP Server Manager to administrators and MCPサーバーユーザー コンシューマーへ。

ステップ4 — 保存と承認 「 MCPサーバーを追加」をクリックします。その後、各ユーザーがサーバーの「 ツール 」セクションを開き、「 今すぐ接続 」をクリックしてAtlassian OAuthを完了させます。するとツールが表示され、「 エージェントプレイグラウンド」から試用できるようになります。

MCP Servers panel showing an unauthorized server in the “You’re not connected to this MCP Server” state with a Connect Now button

「このMCPサーバーに接続されていません」という未承認状態のサーバーと「今すぐ接続」ボタンが表示されているMCPサーバーパネル

認証の仕組み

TrueFoundryは、 インバウンド 認証(クライアントがゲートウェイに対して自身を証明する方法)と、 アウトバウンド認証(ゲートウェイがAtlassianに対して自身を証明する方法)を分離しています。これらのレイヤーは独立しています。

MCP Gateway authentication and authorization flow showing inbound authentication, access control, and outbound authentication as three distinct stages

インバウンド認証、アクセス制御、アウトバウンド認証の3つの段階で構成されるMCPゲートウェイの認証および認可フロー

インバウンド — 対応している4つのメソッド:

‍

Try now.

One gateway for all your models, MCP servers, and agents.
No credit card needed.

Start free
Table of Contents

One Gateway for Every LLM, Agent and MCP Server

Book a 30-min with our AI expert

Book a Demo

The fastest way to build, govern and scale your AI

Book Demo
Summarize with
ChatGPT logo by OpenAI
Perplexity AI logo
Blurry red snowflake on white background, symmetrical frosty design with soft edges and abstract shape.

Discover More

No items found.
October 31, 2026
|
5 min read

Claude Code Subagents: What They Are and How to Use Them

No items found.
October 31, 2026
|
5 min read

Claude Code with Amazon Bedrock: Setup, IAM, and Cost Control

No items found.
October 31, 2026
|
5 min read

Claude Code vs GitHub Copilot: Features, Pricing, and Enterprise Controls

No items found.
Comparing HITL vs HOTL for enterprise AI oversight
October 30, 2026
|
5 min read

Human on the Loop vs Human in the Loop: Which AI Oversight Model Fits Enterprise Teams?

No items found.
No items found.

Recent Blogs

Black left pointing arrow symbol on white background, directional indicator.
Black left pointing arrow symbol on white background, directional indicator.

Frequently asked questions

Atlassian MCPサーバーとは何ですか?

AtlassianのRovo MCPサーバーのことで、https://mcp.atlassian.com/v1/mcpで提供されるリモートModel Context Protocolサーバーです。Jira、Confluence、Compassを、エージェントが呼び出せるツールとして公開し、課題の検索、ページの読み取り、チケットの作成が可能です。OAuth2を使用し、事前に組織の管理者が接続元のドメインを許可リストに追加する必要があります。

Atlassian MCPサーバーを設定するにはどうすればよいですか?

2段階で行います。まず、組織の管理者がApps → AI settings → Rovo MCP server → Allowed domainsで、TrueFoundryのコントロールプレーンのドメインを追加します。次に、TrueFoundryでMCP Gateway → Add MCP Server → Atlassianを開き、URLをhttps://mcp.atlassian.com/v1/mcpに、認証をOAuth2に設定し(client IDやsecretは不要)、コラボレーターを追加して保存し、各ユーザーにConnect Nowをクリックしてもらいます。

Atlassian MCPサーバーは、既存のJiraとConfluenceの権限に従いますか?

はい。各ユーザーは既存のJira、Confluence、Compassの権限で操作するため、誰かの代理で動作するエージェントは、その人が閲覧できるものだけを参照します。これは上限ではなく下限です。ツール単位の切り替えと承認ポリシーで、さらに絞り込んでください。

TrueFoundryを自社のVPCやオンプレミスにデプロイできますか?

はい。TrueFoundryはお客様のVPC、オンプレミス、エアギャップ環境、ハイブリッド環境で動作するため、多数のプロバイダーにまたがってルーティングする場合でも、プロンプトとレスポンスがお客様のドメインの外に出ることはありません。

TrueFoundryは、MCPとAIエージェント全般に対応していますか?

はい。MCP Gateway、Agent Gateway、そしてツール単位のアクセス制御を備えたMCP & Agents Registryが含まれています。LangGraph、CrewAI、AutoGen、または独自のフレームワークで構築されたエージェントを、すべて一元的に統制できます。

既存のオブザーバビリティスタックと統合できますか?

はい。ゲートウェイはOpenTelemetryに準拠しており、Grafana、Datadog、Prometheus、またはお好みのスタックに接続できます。プロンプトからツール、モデルの実行まで、すべてのリクエストを追跡するため、既存のシステムを大幅に変更することなく、統合されたロギングを実現できます。

Take a quick product tour
Start Product Tour
Product Tour