Atlassian

Atlassian MCP Server

Tools for Atlassian products (Confluence and Jira). This integration supports both Atlassian Cloud and Jira Server/Data Center deployments.

What is an MCP Server?

MCP Info

Image Building Info

Available Tools (80)

Tools Details

Tool: confluence_add_comment

Add a comment to a Confluence page.

This tool may perform destructive updates.

Tool: confluence_add_inline_comment

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

This tool may perform destructive updates.

Tool: confluence_add_label

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

This tool may perform destructive updates.

Tool: confluence_create_page

Create a new Confluence page.

This tool may perform destructive updates.

Tool: confluence_delete_attachment

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• Remove outdated or incorrect attachments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

This tool may perform destructive updates.

Tool: confluence_delete_page

Delete an existing Confluence page.

This tool may perform destructive updates.

Tool: confluence_download_attachment

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.

This tool is read-only. It does not modify its environment.

Tool: confluence_download_content_attachments

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.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_attachments

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

This tool is read-only. It does not modify its environment.

Tool: confluence_get_comments

Get comments for a specific Confluence page.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_inline_comments

Get all inline comments for a Confluence page.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_labels

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

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page

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

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page_children

Get child pages and folders of a specific Confluence page.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page_diff

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

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page_history

Get a historical version of a specific Confluence page.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page_images

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.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_page_views

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.

This tool is read-only. It does not modify its environment.

Tool: confluence_get_space_page_tree

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.

This tool is read-only. It does not modify its environment.

Tool: confluence_move_page

Move a Confluence page to a new parent or space.

This tool may perform destructive updates.

Tool: confluence_reply_to_comment

Reply to an existing comment thread on a Confluence page.

This tool may perform destructive updates.

Tool: confluence_search

Search Confluence content using simple terms or CQL.

• Basic search: 'type=page AND space=DEV'
• Personal space search: 'space="~username"' (note: personal space keys starting with ~ must be quoted)
• Search by title: 'title~"Meeting Notes"'
• Use siteSearch: 'siteSearch ~ "important concept"'
• Use text search: 'text ~ "important concept"'
• Recent content: 'created >= "2023-01-01"'
• Content with specific label: 'label=documentation'
• Recently modified content: 'lastModified > startOfMonth("-1M")'
• Content modified this year: 'creator = currentUser() AND lastModified > startOfYear()'
• Content you contributed to recently: 'contributor = currentUser() AND lastModified > startOfWeek()'
• Content watched by user: 'watcher = "user@domain.com" AND type = page'
• Exact phrase in content: 'text ~ ""Urgent Review Required"" AND label = "pending-approval"'
• Title wildcards: 'title ~ "Minutes*" AND (space = "HR" OR space = "Marketing")' Note: Special identifiers need proper quoting in CQL: personal space keys (e.g., "~username"), reserved words, numeric IDs, and identifiers with special characters. limit|integer optional|Maximum number of results (1-50) spaces_filter|string optional|(Optional) Comma-separated list of space keys to filter results by. Overrides the environment variable CONFLUENCE_SPACES_FILTER if provided. Use empty string to disable filtering.

This tool is read-only. It does not modify its environment.

Tool: confluence_search_user

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

• Basic user lookup by full name: 'user.fullname ~ "First Last"' Note: Special identifiers need proper quoting in CQL: personal space keys (e.g., "~username"), reserved words, numeric IDs, and identifiers with special characters. group_name|string optional|Group to search within on Server/DC instances (default: 'confluence-users'). Ignored on Cloud. limit|integer optional|Maximum number of results (1-50)

This tool is read-only. It does not modify its environment.

Tool: confluence_update_page

Update an existing Confluence page.

This tool may perform destructive updates.

Tool: confluence_update_page_section

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.

This tool may perform destructive updates.

Tool: confluence_upload_attachment

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

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

This tool may perform destructive updates.

Tool: confluence_upload_attachments

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

This tool may perform destructive updates.

Tool: jira_add_comment

Add a comment to a Jira issue.

This tool may perform destructive updates.

Tool: jira_add_issues_to_sprint

Add issues to a Jira sprint.

Tool: jira_add_watcher

Add a user as a watcher to a Jira issue.

Tool: jira_add_worklog

Add a worklog entry to a Jira issue.

This tool may perform destructive updates.

Tool: jira_assign_issue

Assign a Jira issue to a user using the dedicated assignment endpoint.

This is more reliable than setting assignee via update_issue, which is silently ignored by some Jira configurations. Uses PUT /issue/{key}/assignee.

Tool: jira_batch_create_issues

Create multiple Jira issues in a batch.

• project_key (required): The project key (e.g., 'PROJ')
• summary (required): Issue summary/title
• issue_type (required): Type of issue (e.g., 'Task', 'Bug')
• description (optional): Issue description in Markdown format
• assignee (optional): Assignee username or email
• components (optional): Array of component names Example: [ {"project_key": "PROJ", "summary": "Issue 1", "issue_type": "Task"}, {"project_key": "PROJ", "summary": "Issue 2", "issue_type": "Bug", "components": ["Frontend"]} ] validate_only|boolean optional|If true, only validates the issues without creating them

This tool may perform destructive updates.

Tool: jira_batch_create_versions

Batch create multiple versions in a Jira project.

• name (required): Name of the version
• startDate (optional): Start date (YYYY-MM-DD)
• releaseDate (optional): Release date (YYYY-MM-DD)
• description (optional): Description of the version Example: [ {"name": "v1.0", "startDate": "2025-01-01", "releaseDate": "2025-02-01", "description": "First release"}, {"name": "v2.0"} ]

This tool may perform destructive updates.

Tool: jira_batch_get_changelogs

Get changelogs for multiple Jira issues (Cloud only).

This tool is read-only. It does not modify its environment.

Tool: jira_create_issue

Create a new Jira issue with optional Epic link or parent for subtasks.

• Set priority: {"priority": {"name": "High"}}
• Add labels: {"labels": ["frontend", "urgent"]}
• Link to parent (for any issue type): {"parent": "PROJ-123"}
• Link to epic: {"epicKey": "EPIC-123"} or {"epic_link": "EPIC-123"}
• Set Fix Version/s: {"fixVersions": [{"id": "10020"}]}
• Custom fields: {"customfield_10010": "value"} assignee|string optional|(Optional) Assignee's user identifier (string): Email, display name, or account ID (e.g., 'user@example.com', 'John Doe', 'accountid:...') components|string optional|(Optional) Comma-separated list of component names to assign (e.g., 'Frontend,API') description|string optional|Issue description in Markdown format

This tool may perform destructive updates.

Tool: jira_create_issue_link

Create a link between two Jira issues.

This tool may perform destructive updates.

Tool: jira_create_remote_issue_link

Create a remote issue link (web link or Confluence link) for a Jira issue.

This tool allows you to add web links and Confluence links to Jira issues. The links will appear in the issue's "Links" section and can be clicked to navigate to external resources.

This tool may perform destructive updates.

Tool: jira_create_sprint

Create Jira sprint for a board.

This tool may perform destructive updates.

Tool: jira_create_version

Create a new fix version in a Jira project.

This tool may perform destructive updates.

Tool: jira_delete_issue

Delete an existing Jira issue.

This tool may perform destructive updates.

Tool: jira_download_attachments

Download attachments from a Jira issue.

Returns attachment contents as base64-encoded embedded resources so that they are available over the MCP protocol without requiring filesystem access on the server.

This tool is read-only. It does not modify its environment.

Tool: jira_edit_comment

Edit an existing comment on a Jira issue.

This tool may perform destructive updates.

Tool: jira_get_agile_boards

Get jira agile boards by name, project key, or type.

This tool is read-only. It does not modify its environment.

Tool: jira_get_all_projects

Get all Jira projects accessible to the current user.

This tool is read-only. It does not modify its environment.

Tool: jira_get_board_issues

Get all issues linked to a specific board filtered by JQL.

• Find Epics: "issuetype = Epic AND project = PROJ"
• Find issues in Epic: "parent = PROJ-123"
• Find by status: "status = 'In Progress' AND project = PROJ"
• Find by assignee: "assignee = currentUser()"
• Find recently updated: "updated >= -7d AND project = PROJ"
• Find by label: "labels = frontend AND project = PROJ"
• Find by priority: "priority = High AND project = PROJ" expand|string optional|Optional fields to expand in the response (e.g., 'changelog'). fields|string optional|Comma-separated fields to return in the results. Use '*all' for all fields, or specify individual fields like 'summary,status,assignee,priority' limit|integer optional|Maximum number of results (1-50) start_at|integer optional|Starting index for pagination (0-based)

This tool is read-only. It does not modify its environment.

Tool: jira_get_field_options

Get allowed option values for a custom field.

Returns the list of valid options for select, multi-select, radio, checkbox, and cascading select custom fields.

Cloud: Uses the Field Context Option API. If context_id is not provided, automatically resolves to the global context.

Server/DC: Uses createmeta to get allowedValues. Requires project_key and issue_type parameters.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue

Get details of a specific Jira issue.

Includes Epic links and relationship information. Use the include parameter to inline enrichments (remote_links, transitions, watchers, changelog, comments, worklogs) so that separate tool calls are not needed.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_dates

Get date information and status transition history for a Jira issue.

Returns dates (created, updated, due date, resolution date) and optionally status change history with time tracking for workflow analysis.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_development_info

Get development information (PRs, commits, branches) linked to a Jira issue.

This retrieves the development panel information that shows linked pull requests, branches, and commits from connected source control systems like Bitbucket, GitHub, or GitLab.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_images

Get all images attached to a Jira issue 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.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_proforma_forms

Get all ProForma forms associated with a Jira issue.

Uses the new Jira Forms REST API. Form IDs are returned as UUIDs.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_sla

Calculate SLA metrics for a Jira issue.

Computes various time-based metrics including cycle time, lead time, time spent in each status, due date compliance, and more.

Working hours can be configured via environment variables:

• JIRA_SLA_WORKING_HOURS_ONLY: Enable working hours filtering (true/false)
• JIRA_SLA_WORKING_HOURS_START: Start time (e.g., "09:00")
• JIRA_SLA_WORKING_HOURS_END: End time (e.g., "17:00")
• JIRA_SLA_WORKING_DAYS: Working days (e.g., "1,2,3,4,5" for Mon-Fri)
• JIRA_SLA_TIMEZONE: Timezone for calculations (e.g., "America/New_York")

This tool is read-only. It does not modify its environment.

Tool: jira_get_issue_watchers

Get the list of watchers for a Jira issue.

This tool is read-only. It does not modify its environment.

Tool: jira_get_issues_development_info

Get development information for multiple Jira issues.

Batch retrieves development panel information (PRs, commits, branches) for multiple issues at once.

This tool is read-only. It does not modify its environment.

Tool: jira_get_link_types

Get all available issue link types.

This tool is read-only. It does not modify its environment.

Tool: jira_get_proforma_form_details

Get detailed information about a specific ProForma form.

Uses the new Jira Forms REST API. Returns form details including ADF design structure.

This tool is read-only. It does not modify its environment.

Tool: jira_get_project_components

Get all components for a specific Jira project.

This tool is read-only. It does not modify its environment.

Tool: jira_get_project_fields

Get the fields available on issues of a project (the create schema), deduplicated across the project's issue types — i.e. which fields tickets in this project have, regardless of whether they are filled.

This tool is read-only. It does not modify its environment.

Tool: jira_get_project_issues

Get all issues for a specific Jira project.

This tool is read-only. It does not modify its environment.

Tool: jira_get_project_versions

Get all fix versions for a specific Jira project.

This tool is read-only. It does not modify its environment.

Tool: jira_get_queue_issues

Get issues from a Jira Service Desk queue.

Server/Data Center only. Not available on Jira Cloud.

This tool is read-only. It does not modify its environment.

Tool: jira_get_service_desk_for_project

Get the Jira Service Desk associated with a project key.

Server/Data Center only. Not available on Jira Cloud.

This tool is read-only. It does not modify its environment.

Tool: jira_get_service_desk_queues

Get queues for a Jira Service Desk.

Server/Data Center only. Not available on Jira Cloud.

This tool is read-only. It does not modify its environment.

Tool: jira_get_sprint_issues

Get jira issues from sprint.

This tool is read-only. It does not modify its environment.

Tool: jira_get_sprints_from_board

Get jira sprints from board by state.

This tool is read-only. It does not modify its environment.

Tool: jira_get_transitions

Get available status transitions for a Jira issue.

This tool is read-only. It does not modify its environment.

Tool: jira_get_user_profile

Retrieve profile information for a specific Jira user.

This tool is read-only. It does not modify its environment.

Tool: jira_get_worklog

Get worklog entries for a Jira issue.

This tool is read-only. It does not modify its environment.

Tool: jira_link_to_epic

Link an existing issue to an epic.

This tool may perform destructive updates.

Tool: jira_remove_issue_link

Remove a link between two Jira issues.

This tool may perform destructive updates.

Tool: jira_remove_watcher

Remove a user from watching a Jira issue.

Tool: jira_search

Search Jira issues using JQL (Jira Query Language).

• Find Epics: "issuetype = Epic AND project = PROJ"
• Find issues in Epic: "parent = PROJ-123"
• Find by status: "status = 'In Progress' AND project = PROJ"
• Find by assignee: "assignee = currentUser()"
• Find recently updated: "updated >= -7d AND project = PROJ"
• Find by label: "labels = frontend AND project = PROJ"
• Find by priority: "priority = High AND project = PROJ" expand|string optional|(Optional) fields to expand. Examples: 'renderedFields', 'transitions', 'changelog' fields|string optional|(Optional) Comma-separated fields to return in the results. Use '*all' for all fields, or specify individual fields like 'summary,status,assignee,priority' limit|integer optional|Maximum number of results (1-50) page_token|string optional|(Optional) Pagination token from a previous search result. Cloud only — Server/DC uses start_at for pagination. projects_filter|string optional|(Optional) Comma-separated list of project keys to filter results by. Overrides the environment variable JIRA_PROJECTS_FILTER if provided. start_at|integer optional|Starting index for pagination (0-based)

This tool is read-only. It does not modify its environment.

Tool: jira_search_assignable_users

Search Jira users assignable in a given project or issue.

Use this when you have a display name / partial name / email fragment and need a concrete identifier (name / key for Server/DC, accountId for Cloud) to feed into assignee, reporter, watcher, etc.

Returns the full result set so the caller can disambiguate when several users match — get_user_profile only resolves one identifier and is not designed for human-name search.

Exactly one of project_key or issue_key must be provided — the underlying API (/user/assignable/search) requires a project or issue context and works without the global "Browse Users" permission that bot accounts in locked-down DC instances often lack.

This tool is read-only. It does not modify its environment.

Tool: jira_search_fields

Search Jira fields by keyword with fuzzy match.

This tool is read-only. It does not modify its environment.

Tool: jira_transition_issue

Transition a Jira issue to a new status.

This tool may perform destructive updates.

Tool: jira_update_issue

Update an existing Jira issue including changing status, adding Epic links, updating fields, etc.

This tool may perform destructive updates.

Tool: jira_update_proforma_form_answers

Update form field answers using the Jira Forms REST API.

This is the primary method for updating form data. Each answer object must specify the question ID, answer type, and value.

⚠️ KNOWN LIMITATION - DATETIME fields: The Jira Forms API does NOT properly preserve time components in DATETIME fields. Only the date portion is stored; times are reset to midnight (00:00:00).

Workaround for DATETIME fields: Use jira_update_issue to directly update the underlying custom fields instead:

1. Get the custom field ID from the form details (question's "jiraField" property)
2. Use jira_update_issue with fields like: {"customfield_XXXXX": "2026-01-09T11:50:00-08:00"}

Example:

# Instead of updating via form (loses time):
# jira_update_proforma_form_answers(issue_key, form_id, [{"questionId": "91", "type": "DATETIME", "value": "..."}])

# Use direct field update (preserves time):
jira_update_issue(issue_key, {"customfield_10542": "2026-01-09T11:50:00-08:00"})

Automatic DateTime Conversion: For DATE and DATETIME fields, you can provide values as:

• ISO 8601 strings (e.g., "2024-12-17T19:00:00Z", "2024-12-17")
• Unix timestamps in milliseconds (e.g., 1734465600000)

The tool automatically converts ISO 8601 strings to Unix timestamps.

Example answers: [ {"questionId": "q1", "type": "TEXT", "value": "Updated description"}, {"questionId": "q2", "type": "SELECT", "value": "Product A"}, {"questionId": "q3", "type": "NUMBER", "value": 42}, {"questionId": "q4", "type": "DATE", "value": "2024-12-17"} ]

Common answer types:

• TEXT: String values
• NUMBER: Numeric values
• DATE: Date values (ISO 8601 string or Unix timestamp in ms)
• DATETIME: DateTime values - ⚠️ USE WORKAROUND ABOVE
• SELECT: Single selection from options
• MULTI_SELECT: Multiple selections (value as list)
• CHECKBOX: Boolean values

This tool may perform destructive updates.

Tool: jira_update_sprint

Update jira sprint.

This tool may perform destructive updates.

Tool: jira_update_version

Update an existing fix version in a Jira project.

Only fields explicitly provided are modified; other attributes of the version are left untouched. Useful for archiving/unarchiving versions, renaming, or shifting release dates without recreating them.

This tool may perform destructive updates.

Use this MCP Server

{
  "mcpServers": {
    "atlassian": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "CONFLUENCE_URL",
        "-e",
        "CONFLUENCE_USERNAME",
        "-e",
        "JIRA_URL",
        "-e",
        "JIRA_USERNAME",
        "-e",
        "CONFLUENCE_API_TOKEN",
        "-e",
        "CONFLUENCE_PERSONAL_TOKEN",
        "-e",
        "JIRA_API_TOKEN",
        "-e",
        "JIRA_PERSONAL_TOKEN",
        "mcp/atlassian"
      ],
      "env": {
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_api_token",
        "CONFLUENCE_PERSONAL_TOKEN": "your_api_token",
        "JIRA_API_TOKEN": "your_api_token",
        "JIRA_PERSONAL_TOKEN": "your_api_token"
      }
    }
  }
}

Why is it safer to run MCP Servers with Docker?