---
canonical_url: "https://docs.composio.dev/toolkits/atlassian_mcp"
markdown_url: "https://docs.composio.dev/toolkits/atlassian_mcp.md"
product: "platform"
version: null
last_updated: null
---
# Atlassian MCP
Atlassian Rovo MCP connects agents to Jira, Jira Service Management, Confluence, Bitbucket, Compass, and Teamwork Graph workflows while respecting existing user permissions.
- **Category:** model context protocol
- **Auth:** DCR_OAUTH
- **Composio-managed OAuth available?** No
- **Tools:** 41
- **Triggers:** 0
- **Slug:** `ATLASSIAN_MCP`
- **Version:** 20260910_00
## Tools
### Addcommenttojiraissue
**Slug:** `ATLASSIAN_MCP_ADD_COMMENT_TO_JIRA_ISSUE`
Add or update a comment on a Jira issue
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `commentId` | string | No | ID of an existing comment to update. If omitted, a new comment is added. |
| `commentBody` | string | Yes | Comment body |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
| `commentVisibility` | object | No | |
| `responseContentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Addteamworkgraphcontext
**Slug:** `ATLASSIAN_MCP_ADD_TEAMWORK_GRAPH_CONTEXT`
Adds a relationship between two entities in the Teamwork Graph (e.g. linking two Jira work items, marking one as blocking another, attaching a remote link, or connecting a Jira work item to an Atlas project or goal).
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `title` | string | No | Optional display label for the target. Used by relationships that surface a title (e.g. remote links); ignored otherwise. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `objectIdentifier` | string | Yes | Identifier of the source entity. Accepts an ARI, a full URL, or a stable key (e.g. ENG-123 for a Jira work item). Format depends on relationshipType. |
| `relationshipType` | string ("jira-work-item-links-jira-work-item" | "jira-work-item-blocks-jira-work-item" | "jira-work-item-links-jira-work-item-remote-link" | "jira-work-item-tracks-atlassian-project" | "jira-work-item-contributes-to-atlassian-goal") | Yes | Type of relationship to create. Determines which entity types 'objectIdentifier' and 'targetObjectIdentifier' must resolve to. |
| `targetObjectIdentifier` | string | Yes | Identifier of the target entity. Accepts an ARI, a full URL, or a stable key (e.g. ATLAS-20426 for an Atlas project). Format depends on relationshipType. |
### Addworklogtojiraissue
**Slug:** `ATLASSIAN_MCP_ADD_WORKLOG_TO_JIRA_ISSUE`
Add or update a worklog on a Jira issue. When worklogId is provided, updates that worklog;
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `started` | string | No | When the work was started (ISO 8601 date-time, e.g. 2026-03-09T09:00:00.000+0000). If omitted, the worklog is booked at the current date/time. |
| `timeSpent` | string | Yes | Time spent (e.g. 2h, 30m, 4d). Required for new worklogs; use to set or change time when updating. |
| `worklogId` | string | No | ID of an existing worklog to update. If omitted, a new worklog is created. |
| `visibility` | object | No | |
| `commentBody` | string | No | Comment body |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Atlassianuserinfo
**Slug:** `ATLASSIAN_MCP_ATLASSIAN_USER_INFO`
Get current user info
### Createcompasscomponent
**Slug:** `ATLASSIAN_MCP_CREATE_COMPASS_COMPONENT`
Create a new Compass component
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | Yes | Name of the component |
| `labels` | array | No | Labels for the component |
| `typeId` | string | Yes | Type ID of the component |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `ownerId` | string | No | Owner ID of the component |
| `description` | string | No | Description of the component |
### Createcompasscomponentrelationship
**Slug:** `ATLASSIAN_MCP_CREATE_COMPASS_COMPONENT_RELATIONSHIP`
Create a relationship between Compass components
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `toComponentId` | string | Yes | The ARI of the target component |
| `fromComponentId` | string | Yes | The ARI of the source component |
| `relationshipType` | string ("DEPENDS_ON" | "DEPENDENCY_OF") | Yes | Type of relationship |
### Createcompasscustomfielddefinition
**Slug:** `ATLASSIAN_MCP_CREATE_COMPASS_CUSTOM_FIELD_DEFINITION`
Create a custom field definition in Compass
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `input` | object | Yes | Input data for creating the custom field definition |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
### Createconfluencefootercomment
**Slug:** `ATLASSIAN_MCP_CREATE_CONFLUENCE_FOOTER_COMMENT`
Create a footer comment on a page or blog post
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `body` | string | Yes | Page/comment body. When contentFormat is "html", use standard HTML for headings (
; inline card text; date ; mention @Name; inline placeholder prompt; macro/extension ; sync block ; media group
file.pdf
; inline media file.pdf. For native Confluence macros use data-extension-type="com.atlassian.confluence.macro.core" and never storage XML (). Omit macroId. Do not invent opaque IDs: only copy data-user-id, data-id, data-collection, data-media-id, data-media-collection, data-resource-id, and data-local-id from existing content or tool output; omit data-local-id on new nodes. Preserve existing data-local-id when editing fetched HTML. Tables support data-number-column, data-layout="default|center|wide|full-width", data-display-mode="fixed", data-width, row/col spans, data-colwidth, and cell data-background. Breakout supports data-breakout="wide|full-width" on details, pre, section, and sync blocks. Follow ADF nesting: task/decision items, headings, and captions are inline-only; list items cannot contain headings/tables/panels/expands; panels cannot contain tables/expands/blockquotes/panels; table cells can contain headings, panels, lists, media, blockquote, decision list, and nested expand () but not nested tables or normal expand. Never wrap content in , , or tags. |
| `pageId` | string | No | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `attachmentId` | string | No | Attachment ID to include |
| `contentFormat` | string ("html" | "markdown" | "adf") | No | Content format for page/comment body. Use "html" to write or read Confluence content as structured HTML. HTML supports standard blocks plus Confluence HTML+ data-type nodes: panels, status, task/decision lists, expands, layouts, cards, media, dates, mentions, macros/extensions, and sync blocks. HTML is round-trip safe and preserves inline comments and existing local IDs. It must follow valid ADF nesting rules: inline-only task/decision items, headings, and captions; no self-nesting panels, expands, tables, or blockquotes. Invalid HTML will be rejected with a descriptive error so you can retry. Use "markdown" for simplified plain text. Defaults vary by tool when omitted. |
| `customContentId` | string | No | Custom content ID to include |
| `parentCommentId` | string | No | Parent comment ID for replies |
### Createconfluenceinlinecomment
**Slug:** `ATLASSIAN_MCP_CREATE_CONFLUENCE_INLINE_COMMENT`
Create an inline comment on specific text in a page or blog post. For top-level comments, provide pageId and inlineCommentProperties (text selection + match counts). For replies, provide parentCommentId only (no pageId or inlineCommentProperties). You must first fetch the page content (e.g. using getConfluencePage) to find the exact text and count how many times it appears. Incorrect or missing inlineCommentProperties can result in a 400 error from the Confluence API.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `body` | string | Yes | Page/comment body. When contentFormat is "html", use standard HTML for headings (
; inline card text; date ; mention @Name; inline placeholder prompt; macro/extension ; sync block ; media group
file.pdf
; inline media file.pdf. For native Confluence macros use data-extension-type="com.atlassian.confluence.macro.core" and never storage XML (). Omit macroId. Do not invent opaque IDs: only copy data-user-id, data-id, data-collection, data-media-id, data-media-collection, data-resource-id, and data-local-id from existing content or tool output; omit data-local-id on new nodes. Preserve existing data-local-id when editing fetched HTML. Tables support data-number-column, data-layout="default|center|wide|full-width", data-display-mode="fixed", data-width, row/col spans, data-colwidth, and cell data-background. Breakout supports data-breakout="wide|full-width" on details, pre, section, and sync blocks. Follow ADF nesting: task/decision items, headings, and captions are inline-only; list items cannot contain headings/tables/panels/expands; panels cannot contain tables/expands/blockquotes/panels; table cells can contain headings, panels, lists, media, blockquote, decision list, and nested expand () but not nested tables or normal expand. Never wrap content in , , or tags. |
| `pageId` | string | No | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw). Use for top-level inline comments only; do not provide with parentCommentId. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("html" | "markdown" | "adf") | No | Content format for page/comment body. Use "html" to write or read Confluence content as structured HTML. HTML supports standard blocks plus Confluence HTML+ data-type nodes: panels, status, task/decision lists, expands, layouts, cards, media, dates, mentions, macros/extensions, and sync blocks. HTML is round-trip safe and preserves inline comments and existing local IDs. It must follow valid ADF nesting rules: inline-only task/decision items, headings, and captions; no self-nesting panels, expands, tables, or blockquotes. Invalid HTML will be rejected with a descriptive error so you can retry. Use "markdown" for simplified plain text. Defaults vary by tool when omitted. |
| `parentCommentId` | string | No | Parent comment ID for replies. When provided, this creates a reply to an existing inline comment thread. Do not provide pageId or inlineCommentProperties. |
| `inlineCommentProperties` | object | No | Required for top-level inline comments (not replies). Provide textSelection, textSelectionMatchCount (total occurrences on the page), and textSelectionMatchIndex (0-based, must be < textSelectionMatchCount). |
### Createconfluencepage
**Slug:** `ATLASSIAN_MCP_CREATE_CONFLUENCE_PAGE`
Create a Confluence page or blog post. When contentFormat is "html" or omitted because HTML is the default, first call the getContentFormatGuide tool with { toolName: "createConfluencePage" } and follow the returned HTML-format guidance. Do not call it when contentFormat is "markdown".
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `body` | string | Yes | Page body. When contentFormat is "html" or omitted, author this field using the HTML-format guidance returned by the getContentFormatGuide tool for createConfluencePage. |
| `title` | string | No | Page or blog post title |
| `status` | string ("current" | "draft") | No | Status (draft for unpublished) |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `spaceId` | string | Yes | Numeric space ID (a Long, e.g. "131073"). A space key (e.g. "ENG") or personal-space key (e.g. "~712020abc") is also accepted and resolved to the numeric ID automatically. |
| `subtype` | string ("live") | No | Page subtype (pages only, ignored for blogs) |
| `parentId` | string | No | ID of the parent to nest the new page under. Accepts the ID of any container that can hold a page — a page, folder, whiteboard, database, embed, or slide (smart links surface as embeds). Applies to pages only; ignored for blog posts. |
| `isPrivate` | boolean | No | Make private |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("html" | "markdown" | "adf") | No | Body format. HTML is the default. When contentFormat is "html" or omitted, first call the getContentFormatGuide tool with { toolName: "createConfluencePage" } and follow the returned HTML-format guidance. Use "markdown" for simplified plain text. |
### Createissuelink
**Slug:** `ATLASSIAN_MCP_CREATE_ISSUE_LINK`
Create a link between two Jira issues. For directional link types (e.g. Blocks): inwardIssue = issue that blocks, outwardIssue = issue that is blocked (e.g. "A is blocked by B" → inwardIssue: B, outwardIssue: A). Use getIssueLinkTypes if link type is unknown.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `type` | string | Yes | Link type name (e.g. Duplicate, Blocks, Clones, Relates). Use getIssueLinkTypes to list available types. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `comment` | string | No | Optional comment on the outward issue. |
| `inwardIssue` | string | Yes | Inward issue key (e.g. HSP-1). |
| `outwardIssue` | string | Yes | Outward issue key (e.g. MKY-1). |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Createjiraissue
**Slug:** `ATLASSIAN_MCP_CREATE_JIRA_ISSUE`
Create a Jira issue. Use additional_fields to set any Jira field that does not have its own parameter (e.g. custom fields, priority, components).
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `parent` | string | No | Parent for subtasks |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `summary` | string | Yes | |
| `projectKey` | string | Yes | Project key |
| `transition` | object | No | Optional workflow transition to apply during creation. Use getTransitionsForJiraIssue to find valid transition IDs. Placed at top level of Jira API request, not inside fields. |
| `description` | string | No | Issue description. With contentFormat "markdown" (default), pass plain text or Markdown as a string. With contentFormat "adf", pass an ADF JSON string or a document object with type "doc". |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
| `issueTypeName` | string | Yes | Type (Task, Bug, Story) |
| `additional_fields` | object | No | REQUIRED for custom fields. This is the ONLY parameter to set priority, labels, custom fields, components, fix versions, or any other Jira fields not listed above. Pass a JSON object with field names as keys. Examples: {"components": [{"name": "Backend"}]}, {"fixVersions": [{"name": "v1.2"}]}, {"priority": {"name": "High"}}, {"labels": ["bug"]}, {"customfield_10001": "value"}. |
| `assignee_account_id` | string | No | Assignee ID |
| `responseContentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Editjiraissue
**Slug:** `ATLASSIAN_MCP_EDIT_JIRA_ISSUE`
Update issue. After updating, returns the issue using the same default read fields as getJiraIssue (summary, description, status, issuetype, priority, labels, components, assignee, reporter, created, updated, resolution, project). Use getJiraIssue with fields ["*all"] or a custom list if you need more.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `fields` | object | Yes | Fields to set, keyed by field name or customfield_* ID. To CLEAR a field, pass an explicit null, e.g. { "resolution": null }. Clearing the resolution is the fix when a reopened issue is blocked from transitioning because it still has a Resolution set. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
| `responseContentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Fetch
**Slug:** `ATLASSIAN_MCP_FETCH`
Get details of a Jira issue or Confluence page by ARI (Atlassian Resource Identifier), if the id is not an ARI, then use a different tool to fetch the content
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `id` | string | Yes | Atlassian Resource Identifier (ARI) from search results, e.g., "ari:cloud:jira:cloudId:issue/10107" or "ari:cloud:confluence:cloudId:page/123456789" |
| `cloudId` | string | No | Not needed for this tool — cloudId is extracted from the ARI automatically |
### Getaccessibleatlassianresources
**Slug:** `ATLASSIAN_MCP_GET_ACCESSIBLE_ATLASSIAN_RESOURCES`
Get cloudId to make tool calls. When a link is provided (e.g. https://site.atlassian.net/*), try passing the site hostname (e.g. site.atlassian.net) as cloudId to other tools first; if that fails, use this tool to list accessible resources.
### Getcompasscomponent
**Slug:** `ATLASSIAN_MCP_GET_COMPASS_COMPONENT`
Get a Compass component by ID
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `componentId` | string | Yes | The ID of the component to get |
| `includeCustomFieldsInResponse` | boolean | No | Whether to include custom fields in the response. Components often track important information in custom fields |
| `includeRelatedLinksInResponse` | boolean | No | Whether to include related links to the Component in the response. Components often track links to repository, documentation, Jira project, operational dashboards, on-call schedule etc with links |
| `includeRelatedComponentsAndDependenciesInResponse` | boolean | No | Whether to include related components and dependencies in the response. This includes all relationships (dependencies, child components, parent components, etc.) that this component has with other components |
### Getcompasscomponents
**Slug:** `ATLASSIAN_MCP_GET_COMPASS_COMPONENTS`
Get a list of Compass components
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `after` | string | No | The cursor to start at. |
| `query` | string | No | The query to search for components. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `filters` | object | No | Additional filters to narrow down the search. Results are returned for all the filters matched |
| `maxResults` | number | No | The maximum number of items to return per page. |
### Getcompasscustomfielddefinitions
**Slug:** `ATLASSIAN_MCP_GET_COMPASS_CUSTOM_FIELD_DEFINITIONS`
Get a list of Compass custom field definitions
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
### Getconfluencecommentchildren
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_COMMENT_CHILDREN`
Get reply(child) comments for a comment
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sort` | string ("id" | "-id" | "created-date" | "-created-date") | No | Sort order |
| `limit` | number | No | Max replies |
| `cursor` | string | No | Pagination cursor |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `commentId` | string | Yes | Parent comment ID |
| `commentType` | string ("footer" | "inline") | Yes | Comment type |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Getconfluencepage
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_PAGE`
Get a Confluence page or blog post by ID, including body content.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `pageId` | string | Yes | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("html" | "markdown" | "adf") | No | Content format for page/comment body. Use "html" to write or read Confluence content as structured HTML. HTML supports standard blocks plus Confluence HTML+ data-type nodes: panels, status, task/decision lists, expands, layouts, cards, media, dates, mentions, macros/extensions, and sync blocks. HTML is round-trip safe and preserves inline comments and existing local IDs. It must follow valid ADF nesting rules: inline-only task/decision items, headings, and captions; no self-nesting panels, expands, tables, or blockquotes. Invalid HTML will be rejected with a descriptive error so you can retry. Use "markdown" for simplified plain text. Defaults vary by tool when omitted. |
### Getconfluencepagedescendants
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_PAGE_DESCENDANTS`
Get child pages of specified page
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `depth` | number | No | Max depth |
| `limit` | number | No | Max descendants |
| `cursor` | string | No | Pagination cursor |
| `pageId` | string | Yes | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
### Getconfluencepagefootercomments
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_PAGE_FOOTER_COMMENTS`
Get footer comments for a page or blog post
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sort` | string ("id" | "-id" | "created-date" | "-created-date") | No | Sort order |
| `limit` | number | No | Max comments |
| `cursor` | string | No | Pagination cursor |
| `pageId` | string | Yes | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `status` | string ("current" | "archived" | "trashed" | "deleted" | "historical" | "draft") | No | Comment status |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
| `includeReplies` | boolean | No | When true, also return reply comments |
| `repliesPerComment` | integer | No | |
### Getconfluencepageinlinecomments
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_PAGE_INLINE_COMMENTS`
Get inline comments for a page or blog post
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sort` | string ("id" | "-id" | "created-date" | "-created-date") | No | Sort order |
| `limit` | number | No | Max comments |
| `cursor` | string | No | Pagination cursor |
| `pageId` | string | Yes | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `status` | string ("current" | "archived" | "trashed" | "deleted" | "historical" | "draft") | No | Comment status |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
| `includeReplies` | boolean | No | When true, also return reply comments |
| `resolutionStatus` | string ("resolved" | "open" | "dangling" | "reopened") | No | Resolution status |
| `repliesPerComment` | integer | No | |
### Getconfluencespaces
**Slug:** `ATLASSIAN_MCP_GET_CONFLUENCE_SPACES`
Get spaces
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `ids` | string | No | Space IDs |
| `keys` | string | No | Space keys |
| `type` | string ("global" | "personal") | No | Space type |
| `limit` | number | No | Max results (default: 25, max: 250) |
| `start` | number | No | Start index |
| `expand` | string | No | Properties to expand |
| `labels` | string | No | Space labels |
| `status` | string ("current" | "archived") | No | Space status |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `favourite` | boolean | No | Favorite spaces only |
| `favoritedBy` | string | No | User favorites |
### Getcontentformatguide
**Slug:** `ATLASSIAN_MCP_GET_CONTENT_FORMAT_GUIDE`
Get the canonical Confluence HTML-format guidance for `createConfluencePage` or `updateConfluencePage`. Use this tool before authoring HTML/default page bodies or fine-grained HTML edits. First call with only `toolName`; if the returned guidance references a follow-up document, call this tool again with the same `toolName` and `reference` set to that single referenced path. Fetch one document per call. Valid `toolName` values: createConfluencePage, updateConfluencePage.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `toolName` | string | Yes | The Confluence page tool whose body you are authoring: `createConfluencePage` or `updateConfluencePage`. Do not pass a content type or `getContentFormatGuide` itself. |
| `reference` | string | No | Forward-compatible provider-specific path for follow-up guidance referenced by the initial response. The current page guide does not emit follow-up references. |
### Getissuelinktypes
**Slug:** `ATLASSIAN_MCP_GET_ISSUE_LINK_TYPES`
Get available Jira issue link types (e.g. Blocks, Duplicate, Clones, Relates). For createIssueLink: inwardIssue = blocker, outwardIssue = blocked (e.g. "A is blocked by B" → inwardIssue: B, outwardIssue: A).
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
### Getjiraissue
**Slug:** `ATLASSIAN_MCP_GET_JIRA_ISSUE`
Get issue details
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `expand` | string | No | Additional issue details to expand in the response (for example, renderedFields or names). |
| `fields` | array | No | Issue fields to return. When omitted or empty, defaults to: summary, description, status, issuetype, priority, labels, components, assignee, reporter, created, updated, resolution, project. Pass "*all" to return every field (including custom fields). Include "comment" to fetch issue comments in fields.comment.comments. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `failFast` | boolean | No | Whether to fail quickly when some fields cannot be loaded instead of partially returning data. |
| `properties` | array | No | Issue property keys to include in the response. |
| `fieldsByKeys` | boolean | No | Whether fields in the request are referenced by field keys instead of IDs. |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `updateHistory` | boolean | No | Whether to update the user's recently viewed projects/history for this issue request. |
| `responseContentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Getjiraissueremoteissuelinks
**Slug:** `ATLASSIAN_MCP_GET_JIRA_ISSUE_REMOTE_ISSUE_LINKS`
Get remote links
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `globalId` | string | No | |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
### Getjiraissuetypemetawithfields
**Slug:** `ATLASSIAN_MCP_GET_JIRA_ISSUE_TYPE_META_WITH_FIELDS`
Get field metadata
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `startAt` | number | No | |
| `maxResults` | number | No | |
| `issueTypeId` | string | Yes | |
| `projectIdOrKey` | string | Yes | |
| `requiredFieldsOnly` | boolean | No | When true (default), returns only the fields that are required to create an issue of this type, reducing response size. Set to false to return all available fields (both required and optional). |
### Getjiraprojectissuetypesmetadata
**Slug:** `ATLASSIAN_MCP_GET_JIRA_PROJECT_ISSUE_TYPES_METADATA`
Get issue types
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `startAt` | number | No | |
| `maxResults` | number | No | |
| `projectIdOrKey` | string | Yes | |
### Getpagesinconfluencespace
**Slug:** `ATLASSIAN_MCP_GET_PAGES_IN_CONFLUENCE_SPACE`
Get pages or blog posts in a space
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sort` | string ("id" | "-id" | "created-date" | "-created-date" | "modified-date" | "-modified-date" | "title" | "-title") | No | Sort order |
| `limit` | integer | No | Max results (default: 25, max: 250) |
| `title` | string | No | Title filter |
| `cursor` | string | No | Pagination cursor |
| `status` | string ("current" | "archived" | "deleted" | "trashed") | No | Page status |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `spaceId` | string | Yes | Space ID |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `contentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Getteamworkgraphcontext
**Slug:** `ATLASSIAN_MCP_GET_TEAMWORK_GRAPH_CONTEXT`
Retrieves connected context from Teamwork Graph for any Atlassian entity. Returns all relationships and linked objects within one traversal – including cross-product and third-party connections. Use when the answer requires connections between entities, not just a single entity's fields.
Supported entry points:
Jira: issues, projects, sprints, versions, comments
Confluence: pages, blogposts, whiteboards, databases, spaces
Goals, Projects, Focus Areas, Tags and updates
People: users, teams, organisations
DevOps: PRs, repos, deployments, services, builds, designs
Loom: videos, meetings
Compass: components
Assets: objects
Incidents, conversations, calendar events, external documents
After calling this tool, call getTeamworkGraphObject on returned ARIs to get full content.
The utilisation of this tool may consume up to 10 Rovo Credits. If the user or organization does not have any Rovo Credits available, the tool call will fail.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `after` | string | No | Pagination cursor for fetching the next page of results. |
| `first` | integer | No | Max number of related items to return. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `timeRange` | object | No | Optional time range to filter relationships by creation or update time. |
| `objectType` | string ("AtlassianGoal" | "AtlassianGoalUpdate" | "AtlassianHomeComment" | "AtlassianHomeTag" | "AtlassianProject" | "AtlassianProjectUpdate" | "AtlassianTeam" | "AtlassianUser" | "CompassComponent" | "ConfluenceBlogPost" | "ConfluenceComment" | "ConfluenceDatabase" | "ConfluencePage" | "ConfluenceSpace" | "ConfluenceWhiteboard" | "ExternalCalendarEvent" | "ExternalConversation" | "ExternalDeployment" | "ExternalDesign" | "ExternalDocument" | "ExternalOrganisation" | "ExternalPosition" | "ExternalPullRequest" | "ExternalRepository" | "ExternalService" | "FocusFocusArea" | "JiraSpace" | "JiraSprint" | "JiraVersion" | "JiraWorkItem" | "JiraWorkItemComment" | "AssetsObject" | "LoomMeeting" | "LoomMeetingRecurrence" | "LoomVideo") | Yes | Type of object to fetch context for. |
| `detailLevel` | string ("summary" | "full") | No | 'summary' (counts/metadata) or 'full' (detailed content). |
| `objectIdentifier` | string | Yes | Identifier for the object. It could be a key (e.g. ENG-1234), ID, ARI, or full URL; format depends on objectType. |
| `relationshipTypes` | array | No | Filter full results to specific relationship types to save tokens (e.g. 'jira-work-item-links-external-build' for Jira work items). |
| `targetObjectTypes` | array | No | Filter results to only include relationships targeting specific object types (e.g. AtlassianUser, ConfluenceComment). |
### Getteamworkgraphobject
**Slug:** `ATLASSIAN_MCP_GET_TEAMWORK_GRAPH_OBJECT`
Fetches the entire available data for one or more objects (Atlassian or third-party) using their ARIs or URLs. Use for the objects gathered from getTeamworkGraphContext tool.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `objects` | array | Yes | A list of object identifiers to hydrate. Supports both ARIs (e.g., 'ari:cloud:jira::issue/123') and full browser URLs (e.g., 'https://mysite.atlassian.net/browse/PROJ-1'). |
### Gettransitionsforjiraissue
**Slug:** `ATLASSIAN_MCP_GET_TRANSITIONS_FOR_JIRA_ISSUE`
Get transitions
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `expand` | string | No | |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `transitionId` | string | No | |
| `sortByOpsBarAndStatus` | boolean | No | |
| `skipRemoteOnlyCondition` | boolean | No | |
| `includeUnavailableTransitions` | boolean | No | |
### Getvisiblejiraprojects
**Slug:** `ATLASSIAN_MCP_GET_VISIBLE_JIRA_PROJECTS`
Get projects
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `action` | string ("view" | "browse" | "edit" | "create") | No | |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `startAt` | number | No | |
| `maxResults` | number | No | |
| `searchString` | string | No | |
| `expandIssueTypes` | boolean | No | |
### Lookupjiraaccountid
**Slug:** `ATLASSIAN_MCP_LOOKUP_JIRA_ACCOUNT_ID`
Lookup user IDs
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `searchString` | string | Yes | |
### Search
**Slug:** `ATLASSIAN_MCP_SEARCH`
Search Jira, Confluence and linked 3P data using Rovo Search, ALWAYS use this tool to search for Jira and Confluence content unless the word CQL or JQL is used in the context. The utilisation of this tool may consume up to 10 Rovo Credits. If the user or organization does not have any Rovo Credits available, the tool call will fail.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | Yes | The search query to use for Rovo Search |
| `cloudId` | string | No | Not needed for this tool — cloudId is derived from your access token automatically |
### Searchconfluenceusingcql
**Slug:** `ATLASSIAN_MCP_SEARCH_CONFLUENCE_USING_CQL`
Search Confluence content (pages, blog posts, comments, attachments) using CQL (Confluence Query Language). CQL is specific to Confluence and is not interchangeable with JQL.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cql` | string | Yes | CQL (Confluence Query Language) query string. CQL is specific to Confluence and is not JQL. Common fields: title, text, space, type, creator, contributor, label, ancestor, parent, lastmodified, created, mention, watcher, space.title, space.key. Use space key (not name) for the space field; use space.title ~ "name" for name search. Content types: page, blogpost, comment, attachment. Escape inner quotes with backslash: title ~ "Q2 \"planning\" review". Examples: title ~ "meeting notes" AND type = page | space.title ~ "Engineering" AND lastmodified >= now("-2w") AND type = page | creator = currentUser() AND type = page | text ~ "Q2 \"planning\" review" AND type = page |
| `next` | boolean | No | Include next page link |
| `prev` | boolean | No | Include previous page link |
| `limit` | number | No | Max results (default: 25, max: 250) |
| `cursor` | string | No | Pagination cursor |
| `expand` | string | No | Properties to expand |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `cqlcontext` | string | No | CQL context for narrowing search scope (e.g., spaceKey) |
### Searchjiraissuesusingjql
**Slug:** `ATLASSIAN_MCP_SEARCH_JIRA_ISSUES_USING_JQL`
Search issues with JQL, total counts only when explicitly requested.
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `jql` | string | Yes | JQL query |
| `fields` | array | No | Issue fields to return. When omitted or empty, defaults to: summary, description, status, issuetype, priority, labels, components, assignee, reporter, created, updated, resolution, project. Pass "*all" to return every field (including custom fields). Include "comment" to fetch issue comments in fields.comment.comments. |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `maxResults` | number | No | Max (50-100) |
| `nextPageToken` | string | No | Page token |
| `searchResultMode` | string ("issues" | "count" | "all") | No | Default "issues". Never count for normal search or if nextPageToken used. If total for same query is known, reuse it. Use "count" only when no trusted count exists and either the user asks or a downstream step needs it. Use "all" only if both count and issues required. |
| `responseContentFormat` | string ("markdown" | "adf") | No | Content format for body content. Use "markdown" for simplified plain text. Use "adf" (Atlassian Document Format, JSON) for full programmatic fidelity. Defaults vary by tool when omitted. |
### Transitionjiraissue
**Slug:** `ATLASSIAN_MCP_TRANSITION_JIRA_ISSUE`
Transition issue status
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `fields` | object | No | |
| `update` | object | No | |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `transition` | object | Yes | |
| `issueIdOrKey` | string | Yes | Issue ID or key (e.g., PROJ-123 or 10000) |
| `historyMetadata` | object | No | |
### Updateconfluencepage
**Slug:** `ATLASSIAN_MCP_UPDATE_CONFLUENCE_PAGE`
Update a Confluence page or blog post. When contentFormat is "html" or omitted because HTML is the default, first call the getContentFormatGuide tool with { toolName: "updateConfluencePage" } and follow the returned HTML-format guidance. Do not call it when contentFormat is "markdown".
#### Input Parameters
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `body` | string | Yes | Replacement page body. When contentFormat is "html" or omitted, author this field using the HTML-format guidance returned by the getContentFormatGuide tool for updateConfluencePage. |
| `title` | string | No | New title |
| `pageId` | string | Yes | Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw) |
| `status` | string ("current" | "draft") | No | Page status |
| `cloudId` | string | Yes | Cloud ID (UUID or site URL) |
| `spaceId` | string | No | Optional numeric space ID (a Long, e.g. "131073"). A space key (e.g. "ENG") or personal-space key (e.g. "~712020abc") is also accepted and resolved to the numeric ID automatically. Provide only for an actual move; omit when the space is unchanged. |
| `parentId` | string | No | ID of the parent to move the page under. Accepts the ID of any container that can hold a page — a page, folder, whiteboard, database, embed, or slide (smart links surface as embeds). Applies to pages only; ignored for blog posts. |
| `contentType` | string ("page" | "blog") | No | Type of content: page or blog post |
| `includeBody` | boolean | No | If true, include the page body in the response; if false, omit it to reduce payload size. |
| `contentFormat` | string ("html" | "markdown" | "adf") | No | Body format. HTML is the default. When contentFormat is "html" or omitted, first call the getContentFormatGuide tool with { toolName: "updateConfluencePage" } and follow the returned HTML-format guidance. Use "markdown" for simplified plain text. |
| `versionMessage` | string | No | Version message |