Best for
- Developers, content creators, and project teams using Atlassian Cloud
- Teams that want Atlassian access inside ChatGPT, Claude, Cursor, or VS Code
- Users who need natural-language search, write, and cross-product workflows
A
Atlassian Rovo MCP Server
Official
Securely connect Atlassian Cloud to AI tools.
- Category
- Collaboration #1 of 55
- Stars
- ★ 1.1k Very popular
- Transport
- Streamable HTTP
- Runtime
- Hosted (no local runtime)
- Credentials
- API key / credential required
- License
- Apache-2.0
- Last commit
66FMRS · C
An official, cloud-hosted Atlassian MCP server for accessing and managing Atlassian Cloud data from compatible AI clients. Capabilities and authentication depend on the product, client, user permissions, and administrator policies; canonical tool identifiers are not listed in the supplied material.
Strongest · Documentation 15/20 Weakest · Reliability 8/20
Why each score
- Reliability 8/20
- The manifest declares two HTTPS streamable-http endpoints, but the supplied material contains no server source, CI, commit history, tests, or evidence of a successful MCP initialization and tool-list handshake. Startup behavior, tool consistency, error handling, and dependency control therefore cannot be verified statically. The score reflects plausible operation only, with substantial deductions for missing reproducible evidence.
- Security and permissions 15/20
- The material documents OAuth 2.1, scoped API tokens, inherited product permissions, organization and site-admin controls, domain restrictions, IP allowlisting, TLS 1.2+, revocation, and audit logging, and it recommends least privilege. Points are deducted because this is an externally hosted service with no disclosed data-retention or processing boundaries, and it supports write operations while providing only recommended rather than enforced human confirmation. No red-line risk is evidenced.
- Maintenance 15/20
- The repository is identified as an official Atlassian project, is not archived, uses Apache-2.0, and declares version 1.1.3. The README provides Atlassian Support, community, and developer-portal channels. Points are deducted because the supplied evidence lacks release cadence, commit activity, dependency-update practice, a security-response process, or demonstrated issue handling; 69 open issues alone do not establish maintenance quality.
- Documentation 15/20
- The README covers clients, supported products, authentication differences, prerequisites, endpoints, API-token configuration, administrative controls, auditing, common errors, workflow examples, and security risks. Points are deducted because it lacks a complete tool-parameter and response reference, rate limits, costs, data-retention details, a compatibility matrix, and verifiable troubleshooting or test evidence. There is also a minor product-scope mismatch between the README and manifest.
- Setup experience 13/20
- The documentation provides one-click links for several mainstream clients, OAuth endpoints, an API-token path, and requirements for local clients using mcp-remote with Node.js 18+. The connection flow is reasonably clear. Points are deducted because setup still depends on client-specific behavior, browser authorization or manual token configuration, and product-specific authentication constraints; no source-level executable installation evidence or end-to-end tests are supplied.
Static review · not runListed 2026-07-29
Read the FMRS scoring method →Fit and risk
What it can accessUses the networkChanges third-party account data
Not for
- Users without an Atlassian Cloud site or relevant product permissions
- Deployments requiring a self-hosted MCP server
- Users unwilling to grant an AI client access to Atlassian data or actions
- Jira Service Management or Bitbucket Cloud workflows requiring OAuth authentication
Required permissions
- Jira and Confluence provide read, write, and search permission groups
- Jira Service Management provides read and write access through API tokens only
- Bitbucket Cloud provides read and write access through scoped API tokens only
- Compass is available through OAuth 2.1 only
- The first OAuth installer for a site must have access to the Atlassian apps requested by the MCP scopes
- Organization administrators can manage domain controls, API-token authentication, app access, and audit logs
Risks and side effects
- AI clients can perform Jira, Confluence, Jira Service Management, Bitbucket, and Compass actions on the user’s behalf
- Prompt injection, indirect prompt injection, and tool-poisoning attacks may cause data exfiltration or unintended changes
- Use least privilege, scoped tokens, and minimal project or workspace access
- Require human confirmation for high-impact or destructive actions and monitor audit logs
Setup
Before you start
Runtime：Hosted (no local runtime)
Add https://mcp.atlassian.com/v1/mcp/authv2 to a supported MCP client. Interactive clients use OAuth 2.1 authorization; headless or service-style setups can use an API token. Local clients require Node.js v18+ and the mcp-remote proxy.
.cursor/mcp.json
{"url":"https://mcp.atlassian.com/v1/mcp/authv2","type":"http"}
Shown for Cursor. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
.vscode/mcp.json
{
"url": "https://mcp.atlassian.com/v1/mcp/authv2",
"type": "http"
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
Check that it works
Connect your client to https://mcp.atlassian.com/v1/mcp/authv2 and complete the OAuth 2.1 flow, then ask 'What Jira projects do I have access to?'; a real answer proves the connection works.
Troubleshooting
- If the client reports “Your site admin must authorize this app,” have a site administrator complete the OAuth 2.1/3LO consent flow
- Verify the Atlassian account, site, product permissions, and requested scopes
- For IP access errors, check the organization’s IP allowlist and relevant VPN or network ranges
- Confirm that an organization administrator enabled API-token authentication and that the token has required scopes
- Custom clients should use /mcp or /mcp/authv2 instead of the legacy /sse endpoint
Things to try
Once connected, you can ask your AI assistant things like:
- Find all open bugs in Project Alpha.
- Create a story titled 'Redesign onboarding'.
- Summarize the Q2 planning page.
- What spaces do I have access to?
Use cases
Search and summarize Jira, Confluence, Jira Service Management, and Bitbucket content
Create or update Jira issues and Confluence pages with natural-language requests
Generate Jira tickets from meeting notes or specifications
Query Compass service components and dependencies
Link Jira issues, Confluence pages, and Compass components
Supported clients
OpenAI ChatGPT
Claude
Cursor
GitHub Copilot
GitHub Copilot CLI
Google Gemini CLI
Amazon Quick Suite
Local MCP-compatible clients via mcp-remotePartial support
Listed from the project's documentation, not tested by this site.
Overview
The official cloud-hosted Atlassian MCP server connects Jira, Confluence, Jira Service Management, Bitbucket Cloud, and Compass to compatible AI clients over Streamable HTTP. It supports search, creation, and management workflows using OAuth 2.1 or API tokens, while honoring the user’s existing Atlassian permissions.
Similar servers
Notion MCP Server
64 · C
Official Notion MCP server for querying, editing, and managing Notion pages and databases via AI agents.
Drive your Claude Code session straight from WhatsApp
Anytype MCP Server
64 · C
Official MCP server that lets AI assistants manage your encrypted Anytype wiki in natural language.
Figma Console MCP
63 · C
Your design system as an API. Connect AI to Figma for extraction, creation, and debugging.
Source revision b74220d41142 Data synced 2026-10-19 Read the FMRS scoring method