Skip to main content
Glama

MCP Atlassian

PyPI Version PyPI - Downloads PePy - Total Downloads Run Tests License Docs

Model Context Protocol (MCP) server for Atlassian products (Confluence and Jira). Supports both Cloud and Server/Data Center deployments.

https://github.com/user-attachments/assets/35303504-14c6-4ae4-913b-7c25ea511c3e

https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785

Quick Start

1. Get Your API Token

Go to 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.

2. Configure Your IDE

Add to your Claude Desktop or Cursor 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 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 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"

Related MCP server: MCP Atlassian Server

Documentation

Full documentation is available at mcp-atlassian.soomiles.com.

Documentation is also available in llms.txt format, which LLMs can consume easily:

Topic

Description

Installation

uvx, Docker, pip, from source

Authentication

API tokens, PAT, OAuth 2.0

Configuration

IDE setup, environment variables

HTTP Transport

SSE, streamable-http, multi-user

Tools Reference

All Jira & Confluence tools

Troubleshooting

Common issues & debugging

Compatibility

Product

Deployment

Support

Confluence

Cloud

Fully supported

Confluence

Server/Data Center

Supported (v6.0+)

Jira

Cloud

Fully supported

Jira

Server/Data Center

Supported (v8.14+)

Key Tools

Jira

Confluence

jira_search - Search with JQL

confluence_search - Search with CQL

jira_get_issue - Get issue details

confluence_get_page - Get page content

jira_create_issue - Create issues

confluence_create_page - Create pages

jira_update_issue - Update issues

confluence_update_page - Update pages

jira_transition_issue - Change status

confluence_add_comment - Add comments

98 tools total — See Tools Reference for the complete list.

Security

Never share API tokens. Keep .env files secure. See SECURITY.md.

Contributing

See CONTRIBUTING.md for development setup.

License

MIT - See LICENSE. Not an official Atlassian product.

Available Tools

35 tools
confluence_add_commentAdd CommentB

Add a comment to a Confluence page.

Inputs: body (required), page_id (required). Returns: result

confluence_add_inline_commentAdd Inline CommentA
Destructive

Add an inline comment anchored to a text selection on a page.

Inputs: body (required), page_id (required), text_selection (required), text_selection_match_count, +1 more. Returns: result

confluence_add_labelAdd LabelA

Add label to Confluence content (pages, blog posts, or attachments).

Useful for:

  • Categorizing attachments (e.g., 'screenshot', 'diagram', 'legal-doc')

  • Tracking status (e.g., 'approved', 'needs-review', 'archived')

  • Filtering content by topic or version

Inputs: name (required), page_id (required). Returns: result

confluence_check_content_permissionsCheck Content PermissionsA
Read-only

Check whether a user or group can perform an operation on specific content.

Wraps POST /wiki/rest/api/content/{id}/permission/check.

Note: This tool is only available for Confluence Cloud. Server/Data Center instances use different permission APIs.

Returns a JSON object with a 'hasPermission' boolean indicating whether the subject has the requested permission on the content.

Inputs: operation (required), content_id (required), user_identifier (required), subject_type. Returns: result

confluence_copy_pageCopy PageA
Destructive

Copy a Confluence page to a new location.

On Confluence Cloud the native copy endpoint is used. On Server/Data Center the page body is fetched and a new page is created manually (attachments are not copied in the Server/DC path).

Inputs: new_title (required), source_page_id (required), destination_space_key (required), copy_attachments, +1 more. Returns: result

confluence_create_pageCreate PageB

Create a new Confluence page.

Inputs: title (required), space_key (required), emoji, content, +8 more. Returns: result

confluence_create_page_from_templateCreate Page from TemplateA

Create a new Cloud page pre-populated with a template's body.

This operation is only available for Confluence Cloud. Fetches the named template and creates a page with its storage-format content. The page can be edited afterwards via confluence_update_page.

Inputs: title (required), space_key (required), template_id (required), parent_id. Returns: result

confluence_delete_attachmentDelete AttachmentA
Destructive

Permanently delete an attachment from Confluence.

Warning: This action cannot be undone! The attachment and ALL its versions will be permanently deleted.

Use this tool to:

  • Remove outdated or incorrect attachments

  • Clean up duplicate files

  • Delete sensitive information that was accidentally uploaded

Best practices:

  • Verify the attachment ID before deletion using get_attachments

  • Consider downloading the attachment first as a backup

  • Check with content owners before deleting shared attachments

Inputs: attachment_id (required). Returns: result

confluence_delete_pageDelete PageA
Destructive

Delete an existing Confluence page.

Inputs: page_id (required). Returns: result

confluence_download_attachmentDownload AttachmentA
Read-only

Download an attachment from Confluence as an embedded resource.

Returns the attachment content as a base64-encoded embedded resource so that it is available over the MCP protocol without requiring filesystem access on the server. Files larger than 50 MB are not downloaded inline; a descriptive error message is returned instead.

Inputs: attachment_id (required).

confluence_download_content_attachmentsDownload All Content AttachmentsA
Read-only

Download all attachments for a Confluence content item as embedded resources.

Returns attachment contents as base64-encoded embedded resources so that they are available over the MCP protocol without requiring filesystem access on the server. Files larger than 50 MB are skipped with an error entry in the summary.

Inputs: content_id (required).

confluence_get_attachmentsGet Content AttachmentsA
Read-only

List all attachments for a Confluence content item (page or blog post).

Returns metadata about attachments including:

  • Attachment ID, title, and file type

  • File size and download URL

  • Creation/modification dates

  • Version information

Important: Confluence API returns 'application/octet-stream' as the media type for most binary files (PNG, JPG, PDF) instead of specific types like 'image/png'. For filtering by file type, using the 'filename' parameter is more reliable (e.g., filename='*.png' pattern matching if supported, or exact filename).

Useful for:

  • Discovering what files are attached to a page

  • Getting attachment IDs for download operations

  • Checking if a specific file exists

  • Listing images/documents for processing

Inputs: content_id (required), limit, start, filename, +1 more. Returns: result

confluence_get_commentsGet CommentsC
Read-only

Get comments for a specific Confluence page.

Inputs: page_id (required). Returns: result

confluence_get_inline_commentsGet Inline CommentsB
Read-only

Get all inline comments for a Confluence page.

Inputs: page_id (required). Returns: result

confluence_get_labelsGet LabelsA
Read-only

Get labels for Confluence content (pages, blog posts, or attachments).

Inputs: page_id (required). Returns: result

confluence_get_pageGet PageA
Read-only

Get content of a specific Confluence page by its ID, or by its title and space key.

Inputs: title, page_id, space_key, include_metadata, +1 more. Returns: result

confluence_get_page_childrenGet Page ChildrenB
Read-only

Get child pages and folders of a specific Confluence page.

Inputs: parent_id (required), limit, start, expand, +3 more. Returns: result

confluence_get_page_diffGet Page Version DiffA
Read-only

Get a unified diff between two versions of a Confluence page.

Inputs: page_id (required), to_version (required), from_version (required). Returns: result

confluence_get_page_historyGet Page HistoryA
Read-only

Get a historical version of a specific Confluence page.

Inputs: page_id (required), version (required), convert_to_markdown. Returns: result

confluence_get_page_imagesGet Page ImagesA
Read-only

Get all images attached to a Confluence page as inline image content.

Filters attachments to images only (PNG, JPEG, GIF, WebP, SVG, BMP) and returns them as base64-encoded ImageContent that clients can render directly. Non-image attachments are excluded.

Files with ambiguous MIME types (application/octet-stream) are detected by filename extension as a fallback. Images larger than 50 MB are skipped with an error entry in the summary.

Inputs: content_id (required).

confluence_get_page_restrictionsGet Page RestrictionsA
Read-only

Get view and edit restrictions for a Confluence page.

Returns the current restriction lists for the read (view) and update (edit) operations. An empty list means the page is unrestricted for that operation.

Inputs: page_id (required). Returns: result

confluence_get_page_templateGet Page TemplateA
Read-only

Get a Cloud page template by ID, including its storage-format body.

Inputs: template_id (required). Returns: result

confluence_get_page_viewsGet Page ViewsA
Read-only

Get view statistics for a Confluence page.

Note: This tool is only available for Confluence Cloud. Server/Data Center instances do not support the Analytics API.

Inputs: page_id (required), include_title. Returns: result

confluence_get_space_page_treeGet Space Page TreeA
Read-only

Get page hierarchy for a Confluence space as a flat list.

Returns pages with parent_id and depth attributes for token-efficient processing. Filter by depth to focus on relevant sections, or find pages by title. Much more efficient than rendering full ASCII trees.

Use this to understand space organization before creating/moving pages.

Inputs: space_key (required), limit. Returns: result

confluence_get_space_permissionsGet Space PermissionsA
Read-only

List all permission assignments for a Confluence space.

Wraps GET /wiki/api/v2/spaces/{id}/permissions.

Note: This tool is only available for Confluence Cloud. Server/Data Center instances use different permission APIs.

Returns a JSON object with a 'results' list of permission assignment objects. Each entry contains the principal (user or group), the operation permitted, and the target. Use this to audit who has access to a space.

Inputs: space_id (required), limit, cursor. Returns: result

confluence_list_page_templatesList Page TemplatesA
Read-only

List Confluence page content templates.

This operation is only available for Confluence Cloud. Returns template metadata (ID, name, description, type) without the full body. Use confluence_get_page_template to fetch a template's body.

Inputs: limit, space_key. Returns: result

confluence_move_pageMove PageB
Destructive

Move a Confluence page to a new parent or space.

Inputs: page_id (required), position, target_parent_id, target_space_key. Returns: result

confluence_reply_to_commentReply to CommentB

Reply to an existing comment thread on a Confluence page.

Inputs: body (required), comment_id (required). Returns: result

confluence_search_userSearch UserA
Read-only

Search Confluence users using CQL (Cloud) or group member API (Server/DC).

Inputs: query (required), limit, group_name. Returns: result

confluence_set_page_restrictionsSet Page RestrictionsA
Destructive

Set view and edit restrictions on a Confluence page.

Replaces all existing restrictions with the provided lists. Omitting all parameters (or passing empty lists) removes all restrictions.

Inputs: page_id (required), edit_users, read_users, edit_groups, +1 more. Returns: result

confluence_update_pageUpdate PageC
Destructive

Update an existing Confluence page.

Inputs: title (required), page_id (required), emoji, content, +9 more. Returns: result

confluence_update_page_sectionUpdate Page SectionA
Destructive

Update a single section of a Confluence page without affecting the rest.

Replaces only the content beneath a named heading, leaving all other sections, macros, layouts, and Confluence-specific elements completely intact. This avoids the data loss that occurs when a full page is downloaded as Markdown, edited, and re-uploaded.

Inputs: page_id (required), new_content (required), heading_text (required), is_minor_edit, +2 more. Returns: result

confluence_upload_attachmentUpload AttachmentA
Destructive

Upload an attachment to Confluence content (page or blog post).

Provide the file either as a server-readable path ('file_path') or as base64-encoded content ('content_base64' together with 'filename'). The base64 form is intended for remote or containerized servers that cannot read host file paths. Exactly one of the two must be supplied.

If the attachment already exists (same filename), a new version is created. This is useful for:

  • Attaching documents, images, or files to a page

  • Updating existing attachments with new versions

  • Adding supporting materials to documentation

Inputs: content_id (required), comment, filename, file_path, +2 more. Returns: result

confluence_upload_attachmentsUpload Multiple AttachmentsA
Destructive

Upload multiple attachments to Confluence content in a single operation.

More efficient than calling upload_attachment multiple times. If files with the same names exist, new versions are created automatically.

Useful for:

  • Bulk uploading documentation assets (diagrams, screenshots, etc.)

  • Adding multiple related files to a page at once

  • Batch updating existing attachments with new versions

Inputs: content_id (required), file_paths (required), comment, minor_edit. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 35 tools

    Disambiguation4/5

    Most tools are clearly separated by resource and action, and detailed descriptions clarify singular/plural and inline/regular variants. A few pairs like get_page_images vs download_content_attachments and get_page_children vs get_space_page_tree could be confused, but the descriptions provide enough context to avoid misselection.

    Naming Consistency4/5

    All tools share a confluence_ prefix and generally follow a verb_noun structure. The pattern is slightly inconsistent because list is only used for list_page_templates while other collection retrievals use get_ (get_comments, get_attachments, get_labels), and confluence_search omits a noun.

    Tool Count2/5

    35 tools is a large surface for an MCP server, exceeding the comfortable well-scoped range. While most operations are legitimate, batching variants and niche endpoints like upload_attachments, download_content_attachments, page_views, and permission checks make the set feel heavy and would benefit from consolidation.

    Completeness3/5

    Page, attachment, and template coverage is strong, including move, copy, restrictions, history, and diff operations. However, comment lifecycle is incomplete with no update/delete comment tools, label deletion is missing, and there is no tool to list spaces or access space metadata; additionally, despite the Atlassian name, Jira is entirely absent.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers