---
title: "Atlassian and Jira MCP Server: mcp-atlassian Setup"
url: "https://mcpshelf.co/servers/atlassian"
description: "mcp-atlassian connects AI assistants to Jira and Confluence, Cloud or Server/Data Center: search, create and update issues and pages. Correct uvx config."
updated: "2026-10-27"
site: "MCP Shelf"
---

# MCP Atlassian (Jira and Confluence)

> Jira issues and Confluence pages, Cloud or self-hosted.

Source: https://mcpshelf.co/servers/atlassian  
Markdown: https://mcpshelf.co/servers/atlassian.md  
Generated: 2026-11-22T22:03:04.743Z

## Facts

- **Name:** MCP Atlassian (Jira and Confluence)
- **Tagline:** Jira issues and Confluence pages, Cloud or self-hosted.
- **Description:** MCP Atlassian (mcp-atlassian) is an open source MCP server that lets AI assistants search, create and update Jira issues and Confluence pages, on Atlassian Cloud or Server and Data Center.
- **Repository:** https://github.com/sooperset/mcp-atlassian
- **Package:** mcp-atlassian 0.23.1 (PyPI)
- **Install:** `claude mcp add atlassian -e JIRA_URL=https://your-company.atlassian.net -e JIRA_USERNAME=you@company.com -e JIRA_API_TOKEN=your-token -e CONFLUENCE_URL=https://your-company.atlassian.net/wiki -e CONFLUENCE_USERNAME=you@company.com -e CONFLUENCE_API_TOKEN=your-token -- uvx mcp-atlassian`
- **Transport:** stdio (local)
- **Auth:** Needs `JIRA_URL`, `JIRA_USERNAME + JIRA_API_TOKEN`
- **Tools exposed:** 98: `jira_get_user_profile`, `jira_search_assignable_users`, `jira_get_issue_watchers`, `jira_add_watcher`, `jira_remove_watcher`, `jira_get_issue`, `jira_search`, `jira_search_fields`, `jira_get_field_options`, `jira_get_project_issues`, `jira_get_transitions`, `jira_get_worklog`, `jira_download_attachments`, `jira_get_issue_images`, `jira_get_agile_boards`, `jira_get_board_issues`, `jira_get_sprints_from_board`, `jira_get_sprint_issues`, `jira_get_link_types`, `jira_create_issue`, `jira_batch_create_issues`, `jira_batch_get_changelogs`, `jira_update_issue`, `jira_assign_issue`, `jira_delete_issue`, `jira_move_issue`, `jira_add_comment`, `jira_edit_comment`, `jira_add_worklog`, `jira_link_to_epic`, `jira_create_issue_link`, `jira_create_remote_issue_link`, `jira_remove_issue_link`, `jira_transition_issue`, `jira_create_sprint`, `jira_update_sprint`, `jira_add_issues_to_sprint`, `jira_move_issues_to_backlog`, `jira_get_project_issue_types`, `jira_get_create_fields`, `jira_get_project_versions`, `jira_get_project_components`, `jira_get_all_projects`, `jira_search_projects`, `jira_get_project_fields`, `jira_get_service_desk_for_project`, `jira_get_service_desk_queues`, `jira_get_queue_issues`, `jira_get_request_types`, `jira_get_request_type_fields`, `jira_create_customer_request`, `jira_create_version`, `jira_batch_create_versions`, `jira_update_version`, `jira_get_issue_proforma_forms`, `jira_get_proforma_form_details`, `jira_update_proforma_form_answers`, `jira_get_issue_dates`, `jira_get_issue_sla`, `jira_get_issue_development_info`, `jira_get_issues_development_info`, `jira_get_project_epic_hierarchy`, `jira_get_cross_project_dependencies`, `confluence_search`, `confluence_get_page`, `confluence_get_page_children`, `confluence_get_space_page_tree`, `confluence_get_comments`, `confluence_get_labels`, `confluence_add_label`, `confluence_create_page`, `confluence_update_page`, `confluence_update_page_section`, `confluence_delete_page`, `confluence_move_page`, `confluence_add_comment`, `confluence_reply_to_comment`, `confluence_get_inline_comments`, `confluence_add_inline_comment`, `confluence_search_user`, `confluence_get_page_history`, `confluence_get_page_diff`, `confluence_get_page_views`, `confluence_upload_attachment`, `confluence_upload_attachments`, `confluence_get_attachments`, `confluence_download_attachment`, `confluence_download_content_attachments`, `confluence_delete_attachment`, `confluence_get_page_images`, `confluence_list_page_templates`, `confluence_get_page_template`, `confluence_create_page_from_template`, `confluence_get_page_restrictions`, `confluence_set_page_restrictions`, `confluence_copy_page`, `confluence_check_content_permissions`, `confluence_get_space_permissions`
- **Category:** Knowledge and work apps (https://mcpshelf.co/categories/knowledge-and-work)
- **Stats:** 6.1K GitHub stars, 215.9K downloads a week, last commit 19 Sept 2026, 0 upvotes on MCP Shelf
- **Install check:** Started in our test
- **Listed:** 2026-10-26
- **Page updated:** 2026-10-27

## Full description

### What is MCP Atlassian (Jira and Confluence)?

**MCP Atlassian (mcp-atlassian) is an open source MCP server that lets AI assistants search, create and update Jira issues and Confluence pages, on Atlassian Cloud or Server and Data Center.**

mcp-atlassian is the most used community server for Atlassian tools. It searches and updates Jira issues with JQL, manages sprints and transitions, and reads and writes Confluence pages, for both Cloud and Server/Data Center.

You can set it to read-only, and you can limit which Confluence spaces and Jira projects it sees.

|  |  |
| --- | --- |
| Made by | sooperset and community contributors (not Atlassian) |
| GitHub | https://github.com/sooperset/mcp-atlassian |
| Licence | MIT |
| PyPI package | [mcp-atlassian](https://pypi.org/project/mcp-atlassian/) 0.23.1 (19 Aug 2026) |
| GitHub stars | 6.1K |
| Downloads | 215.9K a week |
| Last commit | 19 Sept 2026 |
| Tools | 98 |
| Runs on | Your computer |
| Install check | Started in our test |
| Category | [Knowledge and work apps](https://mcpshelf.co/categories/knowledge-and-work) |
| Works with | Claude Code, Cursor, Claude Desktop, VS Code, Codex, Windsurf |
| Setup checked | 27 Oct 2026 |
| Page updated | 27 Oct 2026 |

**Our check:** We ran this exact config on 26 Oct 2026: it started and answered with 98 tools. The npm package called "mcp-atlassian" comes from a different repository (Vijay-Duke/mcp-atlassian). This project is a Python package of the same name, so it runs with uvx.

#### Try asking MCP Atlassian (Jira and Confluence)

- "What Jira tickets are assigned to me in the current sprint?"
- "Summarise the Confluence page about our on-call rota."
- "Move PROJ-123 to In Review and add a comment that the fix is ready."

#### MCP Shelf take

> We started MCP Atlassian (Jira and Confluence) on our own test machine on 26 Oct 2026 and it answered with 98 tools. 58 of the 98 only read; the other 40 can change things. Every tool comes with a useful description, all of them say whether they change things, and the tool list costs about 7,800 tokens of context before you ask a thing. Other directories point at a package with the same name that belongs to someone else; the config on this page installs the real one. It is the most-starred of the 17 servers in its category on our shelf (6.1K stars, with 215.9K downloads a week).

— MCP Shelf tests (numbers from our own runs), tested on 26 Oct 2026

### What tools does MCP Atlassian (Jira and Confluence) have?

We listed 98 tools on 26 Oct 2026. 58 only read; the rest can change things or run commands.

| Tool | Kind | What it is for |
| --- | --- | --- |
| `jira_get_user_profile` | reads | Looks up one Jira user. |
| `jira_search_assignable_users` | reads | Finds people who can be assigned in a project or issue. |
| `jira_get_issue_watchers` | reads | Lists who watches an issue. |
| `jira_add_watcher` | changes | Adds someone as a watcher. |
| `jira_remove_watcher` | changes | Removes a watcher. |
| `jira_get_issue` | reads | Reads one issue with its fields, epic and links. |
| `jira_search` | reads | Finds issues with a JQL query. |
| `jira_search_fields` | reads | Finds field names and ids by keyword, handy for custom fields. |
| `jira_get_field_options` | reads | Lists the allowed values of a custom field. |
| `jira_get_project_issues` | reads | Lists the issues in a project. |
| `jira_get_transitions` | reads | Shows which statuses an issue can move to next. |
| `jira_get_worklog` | reads | Reads time logged on an issue. |
| `jira_download_attachments` | reads | Fetches an issue's attachments. |
| `jira_get_issue_images` | reads | Fetches an issue's image attachments so the assistant can look at them. |
| `jira_get_agile_boards` | reads | Finds Scrum and Kanban boards. |
| `jira_get_board_issues` | reads | Lists the issues on a board, with an optional JQL filter. |
| `jira_get_sprints_from_board` | reads | Lists a board's sprints by state. |
| `jira_get_sprint_issues` | reads | Lists the issues in a sprint. |
| `jira_get_link_types` | reads | Lists link types such as blocks or duplicates. |
| `jira_create_issue` | changes | Opens a new issue, sub-task or epic child. |
| `jira_batch_create_issues` | changes | Opens many issues in one call, with a dry-run option. |
| `jira_batch_get_changelogs` | reads | Reads the change history of many issues (Cloud only). |
| `jira_update_issue` | changes | Edits an issue's fields. |
| `jira_assign_issue` | changes | Assigns an issue to someone. |
| `jira_delete_issue` | changes | Deletes an issue. |
| `jira_move_issue` | changes | Moves an issue to another project (Cloud only). |
| `jira_add_comment` | changes | Comments on an issue. |
| `jira_edit_comment` | changes | Edits an existing comment. |
| `jira_add_worklog` | changes | Logs time against an issue. |
| `jira_link_to_epic` | changes | Puts an issue under an epic. |
| `jira_create_issue_link` | changes | Links two issues, for example "blocks". |
| `jira_create_remote_issue_link` | changes | Adds a web or Confluence link to an issue. |
| `jira_remove_issue_link` | changes | Removes a link between issues. |
| `jira_transition_issue` | changes | Moves an issue to a new status. |
| `jira_create_sprint` | changes | Creates a sprint on a board. |
| `jira_update_sprint` | changes | Renames, starts, closes or re-dates a sprint. |
| `jira_add_issues_to_sprint` | changes | Pulls issues into a sprint. |
| `jira_move_issues_to_backlog` | changes | Sends issues back to the backlog. |
| `jira_get_project_issue_types` | reads | Lists the issue types a project allows. |
| `jira_get_create_fields` | reads | Lists the fields needed to create a given issue type. |
| `jira_get_project_versions` | reads | Lists a project's fix versions. |
| `jira_get_project_components` | reads | Lists a project's components. |
| `jira_get_all_projects` | reads | Lists every project you can see. |
| `jira_search_projects` | reads | Finds projects by name or key. |
| `jira_get_project_fields` | reads | Lists the fields used across a project's issue types. |
| `jira_get_service_desk_for_project` | reads | Finds the service desk behind a project (Server and Data Center). |
| `jira_get_service_desk_queues` | reads | Lists a service desk's queues (Server and Data Center). |
| `jira_get_queue_issues` | reads | Lists the requests in a queue (Server and Data Center). |
| `jira_get_request_types` | reads | Lists the request types of a service desk. |
| `jira_get_request_type_fields` | reads | Lists the fields a request type asks for. |
| `jira_create_customer_request` | changes | Raises a Jira Service Management request. |
| `jira_create_version` | changes | Creates a fix version. |
| `jira_batch_create_versions` | changes | Creates several fix versions at once. |
| `jira_update_version` | changes | Edits or releases a fix version. |
| `jira_get_issue_proforma_forms` | reads | Lists the forms attached to an issue. |
| `jira_get_proforma_form_details` | reads | Reads one form's questions and answers. |
| `jira_update_proforma_form_answers` | changes | Fills in answers on an issue's form. |
| `jira_get_issue_dates` | reads | Reads an issue's key dates and status history. |
| `jira_get_issue_sla` | reads | Works out cycle time and other SLA figures for an issue. |
| `jira_get_issue_development_info` | reads | Shows branches, commits and pull requests linked to an issue. |
| `jira_get_issues_development_info` | reads | The same for many issues at once. |
| `jira_get_project_epic_hierarchy` | reads | Groups a project's epics under their parents across projects. |
| `jira_get_cross_project_dependencies` | reads | Finds links from a project's issues into other projects. |
| `confluence_search` | reads | Finds pages by words or a CQL query. |
| `confluence_get_page` | reads | Reads a page by id, or by title and space. |
| `confluence_get_page_children` | reads | Lists the pages under a page. |
| `confluence_get_space_page_tree` | reads | Lists a whole space's page tree. |
| `confluence_get_comments` | reads | Reads a page's comments. |
| `confluence_get_labels` | reads | Reads a page's labels. |
| `confluence_add_label` | changes | Adds a label. |
| `confluence_create_page` | changes | Creates a page, from Markdown or storage format. |
| `confluence_update_page` | changes | Replaces a page's content. |
| `confluence_update_page_section` | changes | Rewrites one section of a page and leaves the rest alone. |
| `confluence_delete_page` | changes | Deletes a page. |
| `confluence_move_page` | changes | Moves a page to a new parent or space. |
| `confluence_add_comment` | changes | Comments on a page. |
| `confluence_reply_to_comment` | changes | Replies in a comment thread. |
| `confluence_get_inline_comments` | reads | Reads comments pinned to text on a page. |
| `confluence_add_inline_comment` | changes | Pins a comment to a piece of text. |
| `confluence_search_user` | reads | Finds Confluence users. |
| `confluence_get_page_history` | reads | Reads an older version of a page. |
| `confluence_get_page_diff` | reads | Shows what changed between two versions. |
| `confluence_get_page_views` | reads | Reads view counts for a page (Cloud only). |
| `confluence_upload_attachment` | changes | Attaches a file to a page. |
| `confluence_upload_attachments` | changes | Attaches several files at once. |
| `confluence_get_attachments` | reads | Lists a page's attachments. |
| `confluence_download_attachment` | reads | Fetches one attachment. |
| `confluence_download_content_attachments` | reads | Fetches every attachment on a page. |
| `confluence_delete_attachment` | changes | Deletes an attachment for good. |
| `confluence_get_page_images` | reads | Fetches a page's images so the assistant can look at them. |
| `confluence_list_page_templates` | reads | Lists page templates (Cloud). |
| `confluence_get_page_template` | reads | Reads one template's body (Cloud). |
| `confluence_create_page_from_template` | changes | Creates a page from a template (Cloud). |
| `confluence_get_page_restrictions` | reads | Shows who can view or edit a page. |
| `confluence_set_page_restrictions` | changes | Changes who can view or edit a page. |
| `confluence_copy_page` | changes | Copies a page to a new place. |
| `confluence_check_content_permissions` | reads | Checks whether a person or group may do something with a page. |
| `confluence_get_space_permissions` | reads | Lists who has which rights in a space. |

#### How clearly it describes its tools

98 of 98 tools have a description and 98 of 98 say whether they change things. The tool list takes at least ~7,800 tokens of context. Every tool says whether it only reads or can change things, so a client can ask before the risky ones. The tool list is large: switch off the tools you do not use if your client allows it.

### How do I install MCP Atlassian (Jira and Confluence)?

#### Install steps from the MCP Atlassian (Jira and Confluence) README

Copied from the project's [README on GitHub](https://github.com/sooperset/mcp-atlassian#readme) on 16 Nov 2026 under its MIT licence.

##### Quick Start

###### 1. Get Your API Token

Go to [https://id.atlassian.com/manage-profile/security/api-tokens](https://id.atlassian.com/manage-profile/security/api-tokens) and create a token.

> For Server/Data Center, use a Personal Access Token instead. See [Authentication](https://mcp-atlassian.soomiles.com/docs/authentication).

###### 2. Configure Your IDE

Add to your Claude Desktop, Cursor, or GitHub Copilot MCP configuration:

```
{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "uvx",
      "args": ["mcp-atlassian"],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}
```

> **Server/Data Center users**: Use `JIRA_PERSONAL_TOKEN` instead of `JIRA_USERNAME` + `JIRA_API_TOKEN`. See [Authentication](https://mcp-atlassian.soomiles.com/docs/authentication) for details.

###### Autohand Code

Use the same `uvx` server with your Atlassian credentials:

```
autohand mcp add mcp-atlassian env \
  JIRA_URL=https://your-company.atlassian.net \
  JIRA_USERNAME=your.email@company.com \
  JIRA_API_TOKEN=your_api_token \
  CONFLUENCE_URL=https://your-company.atlassian.net/wiki \
  CONFLUENCE_USERNAME=your.email@company.com \
  CONFLUENCE_API_TOKEN=your_api_token \
  uvx mcp-atlassian
```

Add `--scope project` after `add` to keep the configuration in the current
project. See [Autohand Code](https://github.com/autohandai/code-cli/) for current
installation and CLI details.

###### 3. Start Using

Ask your AI assistant to:

- **"Find issues assigned to me in PROJ project"**
- **"Search Confluence for onboarding docs"**
- **"Create a bug ticket for the login issue"**
- **"Update the status of PROJ-123 to Done"**

#### What you need first

- uv (for uvx)
- An Atlassian API token (Cloud) or personal access token (Server/Data Center)

#### Claude Code

Where: Your terminal, in the project folder

```bash
claude mcp add atlassian -e JIRA_URL=https://your-company.atlassian.net -e JIRA_USERNAME=you@company.com -e JIRA_API_TOKEN=your-token -e CONFLUENCE_URL=https://your-company.atlassian.net/wiki -e CONFLUENCE_USERNAME=you@company.com -e CONFLUENCE_API_TOKEN=your-token -- uvx mcp-atlassian
```

For Server or Data Center, swap JIRA_USERNAME and JIRA_API_TOKEN for JIRA_PERSONAL_TOKEN (and the same for Confluence). Leave out the Confluence variables to load only the Jira tools.

#### Cursor

Where: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

```json
{
  "mcpServers": {
    "atlassian": {
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "you@company.com",
        "JIRA_API_TOKEN": "your-token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "you@company.com",
        "CONFLUENCE_API_TOKEN": "your-token"
      }
    }
  }
}
```

#### Claude Desktop

Where: claude_desktop_config.json (Settings → Developer → Edit Config)

```json
{
  "mcpServers": {
    "atlassian": {
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "you@company.com",
        "JIRA_API_TOKEN": "your-token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "you@company.com",
        "CONFLUENCE_API_TOKEN": "your-token"
      }
    }
  }
}
```

#### VS Code

Where: .vscode/mcp.json in your project

```json
{
  "servers": {
    "atlassian": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "you@company.com",
        "JIRA_API_TOKEN": "your-token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "you@company.com",
        "CONFLUENCE_API_TOKEN": "your-token"
      }
    }
  }
}
```

#### Codex

Where: ~/.codex/config.toml, shared by the Codex CLI, IDE extension and ChatGPT desktop app

```
[mcp_servers.atlassian]
command = "uvx"
args = ["mcp-atlassian"]

[mcp_servers.atlassian.env]
JIRA_URL = "https://your-company.atlassian.net"
JIRA_USERNAME = "you@company.com"
JIRA_API_TOKEN = "your-token"
CONFLUENCE_URL = "https://your-company.atlassian.net/wiki"
CONFLUENCE_USERNAME = "you@company.com"
CONFLUENCE_API_TOKEN = "your-token"
```

Or run: `codex mcp add atlassian --env JIRA_URL=https://your-company.atlassian.net --env JIRA_USERNAME=you@company.com --env JIRA_API_TOKEN=your-token --env CONFLUENCE_URL=https://your-company.atlassian.net/wiki --env CONFLUENCE_USERNAME=you@company.com --env CONFLUENCE_API_TOKEN=your-token -- uvx mcp-atlassian`

#### Windsurf

Where: ~/.codeium/windsurf/mcp_config.json

```json
{
  "mcpServers": {
    "atlassian": {
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "you@company.com",
        "JIRA_API_TOKEN": "your-token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "you@company.com",
        "CONFLUENCE_API_TOKEN": "your-token"
      }
    }
  }
}
```

#### ChatGPT

Where: Not supported

Not supported as a local server. The project can run over streamable HTTP for remote use, but ChatGPT cannot send the Atlassian token, so Atlassian's own hosted Rovo server is the better route for ChatGPT on Cloud.

Add "READ_ONLY_MODE": "true" to env while you try it out.

Checked against the project's own install docs on 27 Oct 2026: https://github.com/sooperset/mcp-atlassian#readme, https://mcp-atlassian.soomiles.com/docs/authentication

### How do I configure MCP Atlassian (Jira and Confluence)?

| Setting | Kind | Required | What it does |
| --- | --- | --- | --- |
| `JIRA_URL` | env | yes | Your Jira address. Leave out the Jira variables to use Confluence only. Example: `https://your-company.atlassian.net` |
| `JIRA_USERNAME + JIRA_API_TOKEN` | env | yes | For Atlassian Cloud: your account email and an API token from id.atlassian.com. Example: `you@company.com / ATATT3x...` |
| `JIRA_PERSONAL_TOKEN` | env | no | For Jira Server or Data Center: a personal access token instead of email plus API token. Example: `NjM0...` |
| `CONFLUENCE_URL` | env | no | Your Confluence address, with /wiki on Cloud. Leave out to use Jira only. Example: `https://your-company.atlassian.net/wiki` |
| `CONFLUENCE_USERNAME + CONFLUENCE_API_TOKEN` | env | no | Confluence credentials, the same kind as Jira's. On Server and Data Center use CONFLUENCE_PERSONAL_TOKEN. Example: `you@company.com / ATATT3x...` |
| `READ_ONLY_MODE` | env | no | Turns off every tool that creates, edits or deletes. Example: `true` |
| `ENABLED_TOOLS` | env | no | Offers only the tools you list, which also keeps the prompt small. Example: `jira_search,jira_get_issue,confluence_search` |
| `JIRA_PROJECTS_FILTER / CONFLUENCE_SPACES_FILTER` | env | no | Limits searches to the projects or spaces you list. Example: `PROJ,DEV` |

### What can MCP Atlassian (Jira and Confluence) read and change?

**It can read**

- Every Jira project and Confluence space your account can open, including attachments and history

**It can change**

- Creates, edits, moves and deletes issues, pages, comments, sprints and attachments
- Can change page restrictions

**Safer setup:** Set READ_ONLY_MODE=true until you trust it, and narrow it with ENABLED_TOOLS and the project and space filters.

### Good for

- Turning a conversation into well-formed Jira tickets
- Summarising a sprint or an epic
- Finding the Confluence page that answers a question

### MCP Atlassian (Jira and Confluence) not working? Common fixes

**401 Unauthorized on Atlassian Cloud**
Use your account email as the username and an API token, not your password. Check the URL has no trailing path for Jira and ends in /wiki for Confluence.

**401 on Jira Server or Data Center**
Use JIRA_PERSONAL_TOKEN (and CONFLUENCE_PERSONAL_TOKEN) instead of username and API token.

**SSL certificate errors on a self-hosted instance**
Set JIRA_SSL_VERIFY=false and CONFLUENCE_SSL_VERIFY=false only if you trust the network, or add your company's certificate authority to the machine.

**The assistant ignores the right tool among almost 100**
Set ENABLED_TOOLS to the dozen you actually use.

### What are the alternatives to MCP Atlassian (Jira and Confluence)?

| Server | What it does | Tools | Runs on | Licence | Stars |
| --- | --- | --- | --- | --- | --- |
| [MCP Atlassian (Jira and Confluence)](https://mcpshelf.co/servers/atlassian) | Jira issues and Confluence pages, Cloud or self-hosted. | 98 | Your computer | MIT | 6.1K |
| [Basic Memory](https://mcpshelf.co/servers/basic-memory) | Long-term memory as plain Markdown files you own. | 27 | Your computer | AGPL-3.0-or-later | 4.4K |
| [LinkedIn MCP Server](https://mcpshelf.co/servers/linkedin) | Read LinkedIn profiles, companies and job posts with your own login. | 20 | Your computer | Apache-2.0 | 4K |
| [arXiv MCP Server](https://mcpshelf.co/servers/arxiv) | Search arXiv, download papers and read them in full. | 19 | Your computer | Apache-2.0 | 3.2K |
| [TradingView MCP](https://mcpshelf.co/servers/tradingview) | Prices, indicators, screeners and backtests for stocks, crypto and forex, no account needed. | 37 | Your computer or hosted | MIT | 5.2K |
| [Obsidian MCP](https://mcpshelf.co/servers/obsidian) | Search, read and edit the notes in your Obsidian vault. | 15 | Your computer | MIT | 4.5K |

### MCP Atlassian (Jira and Confluence) FAQ

#### How do I add MCP Atlassian to Claude Code?

Run claude mcp add mcp-atlassian with -e flags for JIRA_URL, JIRA_USERNAME and JIRA_API_TOKEN (and the Confluence equivalents if you want them), then -- uvx mcp-atlassian. You need uv installed first.

#### How do I connect Jira to Cursor with MCP Atlassian?

Add an mcpServers entry to ~/.cursor/mcp.json that runs uvx mcp-atlassian, with JIRA_URL, your email and an API token in env. Create the token at id.atlassian.com under Security, API tokens.

#### Is MCP Atlassian made by Atlassian?

No. It is an open source project by sooperset and contributors, MIT licensed. Atlassian runs its own hosted Rovo MCP server for Cloud; mcp-atlassian is the choice for Server and Data Center or when you want to run it yourself.

#### Does MCP Atlassian work with Jira Server and Data Center?

Yes. Use a personal access token in JIRA_PERSONAL_TOKEN instead of a username and API token. A few tools are Cloud only, and the service desk queue tools are Server and Data Center only.

#### Is MCP Atlassian safe to use on our Jira?

It acts with your token's permissions, so it can change what you can change. Set READ_ONLY_MODE=true to block every write, and use ENABLED_TOOLS plus the project and space filters to narrow what it sees.

#### Is MCP Atlassian free?

Yes. The server is MIT licensed and runs on your machine. It uses the Jira and Confluence APIs that come with your existing Atlassian licence.

#### Why does MCP Atlassian return 401 Unauthorized?

On Cloud, check JIRA_USERNAME is your Atlassian email and the token is an API token, not your password. On Server or Data Center, use JIRA_PERSONAL_TOKEN instead of the username and token pair.

#### Can I use MCP Atlassian with only Jira or only Confluence?

Yes. Set only the variables for the product you want. The other product's tools are left out, which also shortens the tool list the assistant has to choose from.

#### Can I use MCP Atlassian in VS Code?

Yes, through GitHub Copilot. In .vscode/mcp.json, add a server named atlassian with type stdio that runs uvx mcp-atlassian, with JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME and CONFLUENCE_API_TOKEN set under env. Then switch Copilot Chat to Agent mode to use its tools.

#### Does MCP Atlassian work with Codex?

Yes. Add an [mcp_servers.atlassian] table to ~/.codex/config.toml with the command and args from the Codex tab, and JIRA_URL, JIRA_USERNAME, JIRA_API_TOKEN, CONFLUENCE_URL, CONFLUENCE_USERNAME and CONFLUENCE_API_TOKEN in its env table. The Codex CLI and IDE extension share that file.

Full docs on GitHub: https://github.com/sooperset/mcp-atlassian

## Notes for agents

Fetch these instead of parsing the HTML page:

- llms.txt: https://mcpshelf.co/llms.txt
- llms-full.txt: https://mcpshelf.co/llms-full.txt
- ai.txt: https://mcpshelf.co/ai.txt
- Full catalog (.md): https://mcpshelf.co/catalog.md
- API spec: https://mcpshelf.co/openapi.json
- MCP server: https://mcpshelf.co/mcp
- MCP manifest: https://mcpshelf.co/.well-known/mcp.json
- Developer docs: https://mcpshelf.co/developers

MCP endpoint (Streamable HTTP, no key): https://mcpshelf.co/mcp. REST API: https://mcpshelf.co/api/v1.

