> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to the Atlassian Rovo MCP server

The Atlassian Rovo MCP connector routes your AI agent's tool calls to Atlassian Rovo's own MCP server through Scalekit. Each user signs in to Atlassian Rovo once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 40 tools.

**Authentication:** OAuth 2.1/DCR
**Categories:** Project Management, Productivity, Collaboration
**Tools:** 40: 26 read, 14 write, 0 destructive
**Users sign in with:** OAuth
**OAuth app:** Scalekit's or your own
**Built by:** Vendor MCP
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=ATLASSIANMCP)

## What you can do

- **Manage Jira issues**: create, edit, transition, comment on, and link issues; add worklogs
- **Search with JQL**: query issues using Jira Query Language with full field and filter support
- **Work with Confluence**: create, update, and retrieve pages; add footer and inline comments
- **Manage Compass components**: create, get, and search services, libraries, and applications; define custom fields and relationships
- **Look up users and resources**: resolve Atlassian account IDs, list accessible cloud sites, and find project metadata
- **Fetch Atlassian content**: retrieve any Atlassian object by its ARI or URL (e.g. a Jira issue or Confluence page URL)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Atlassian Rovo MCP connection

   In **AgentKit > Connections**, create an Atlassian Rovo MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

   Scalekit credentials are available for Atlassian Rovo MCP server, so you don't need to register an OAuth app. To show your own app on the consent screen, use your own credentials instead.

   **Use your own OAuth app:**

   Atlassian Rovo MCP uses Dynamic Client Registration (DCR) — no client ID or secret is needed. The only step is registering your Scalekit redirect URI as an allowed domain in Atlassian Administration.

   1. ### Copy the redirect URI from Scalekit

      In the [Scalekit dashboard](https://app.scalekit.com), go to **AgentKit** > **Connections** > **Create Connection**. Find **Atlassian Rovo MCP** and click **Create**. Copy the redirect URI — it looks like `https://<SCALEKIT_ENVIRONMENT_URL>/sso/v1/oauth/<CONNECTION_ID>/callback`.

      > Image: Copy redirect URI from Scalekit dashboard for Atlassian Rovo MCP

   2. ### Open the Rovo MCP server settings in Atlassian

      - Go to [admin.atlassian.com](https://admin.atlassian.com) and select your organisation.
      - In the left sidebar, expand **Rovo** and click **Rovo access**.
      - Click **Rovo MCP server** in the submenu.
      - Select the **Domains** tab at the top of the page.

      > note: Admin access required
      >
      > You must be an Atlassian organisation admin to access these settings. If you don't see **Rovo** in the sidebar, your organisation may not have Rovo enabled.

   3. ### Add the redirect URI as a domain

      - Under **Your domains**, click **Add domain**.

      > Image: Your domains section in Atlassian Rovo MCP server administration

      - In the **Add domain** dialog, paste the redirect URI from Scalekit into the **Domain** field.
      - Accept the terms and click **Add**.

      > Image: Add domain dialog in Atlassian Rovo MCP server

      Once added, Scalekit automatically registers the OAuth client via DCR and handles token management for every user who authorizes the connection — no further configuration needed.

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'atlassianmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Atlassian Rovo MCP:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'atlassianmcp_atlassianuserinfo',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "atlassianmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Atlassian Rovo MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="atlassianmcp_atlassianuserinfo",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'atlassianmcp_atlassianuserinfo',
  toolInput: {},
  connector: 'atlassianmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="atlassianmcp_atlassianuserinfo",
    tool_input={},
    connection_name="atlassianmcp",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `atlassianmcp_atlassianuserinfo`

AtlassianUserInfo · Read-only

Retrieve the profile information for the currently authenticated Atlassian user.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `atlassianmcp_fetch`

Fetch · Read-only

Fetch details about any Atlassian object by its ARI (Atlassian Resource Identifier) or URL.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): An ARI or URL identifying the object (e.g. ari:cloud:jira:...:issue/10059 or https://site.atlassian.net/browse/KAN-1).
- `cloudId` (`string`, optional): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.

Example input: `{"id":"<id>"}`

### `atlassianmcp_getaccessibleatlassianresources`

GetAccessibleAtlassianResources · Read-only

List all Atlassian cloud sites accessible to the authenticated user, including their cloud IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `atlassianmcp_getcompasscomponent`

GetCompassComponent · Read-only

Retrieve details of a specific Compass component by its ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `componentId` (`string`, required): The ID of the component to get
- `includeCustomFieldsInResponse` (`boolean`, optional): Set to true to include custom field values in the component response. Default: `true`.
- `includeRelatedComponentsAndDependenciesInResponse` (`boolean`, optional): Set to true to include related components and dependencies. Default: `false`.
- `includeRelatedLinksInResponse` (`boolean`, optional): Set to true to include related links in the component response. Default: `true`.

Example input: `{"cloudId":"<cloudId>","componentId":"<componentId>"}`

### `atlassianmcp_getcompasscomponents`

GetCompassComponents · Read-only

Search and list Compass components in a workspace, with optional filters.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `after` (`string`, optional): Cursor for fetching the next page of results.
- `filters` (`object`, optional): Filter criteria for Compass components as JSON (e.g. {"typeIds": ["SERVICE"]}).
- `maxResults` (`number`, optional): Maximum number of results to return per page. Default: `10`.
- `query` (`string`, optional): Search query to find Atlassian content across Jira and Confluence.

Example input: `{"cloudId":"<cloudId>"}`

### `atlassianmcp_getcompasscustomfielddefinitions`

GetCompassCustomFieldDefinitions · Read-only

List all custom field definitions configured in a Compass workspace.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.

Example input: `{"cloudId":"<cloudId>"}`

### `atlassianmcp_getconfluencecommentchildren`

GetConfluenceCommentChildren · Read-only

Retrieve replies to a specific Confluence comment.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `commentId` (`string`, required): The ID of the Confluence comment to retrieve children for.
- `commentType` (`string`, required): Type of comment to retrieve children for: footer or inline. One of: `footer`, `inline`.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.
- `cursor` (`string`, optional): Cursor string for paginating through results.
- `limit` (`number`, optional): Maximum number of items to return.
- `sort` (`string`, optional): Sort order for results (e.g. created-date, -modified, title). One of: `id`, `-id`, `created-date`, `-created-date`.

Example input: `{"cloudId":"<cloudId>","commentId":"<commentId>","commentType":"footer"}`

### `atlassianmcp_getconfluencepage`

GetConfluencePage · Read-only

Retrieve the content and metadata of a specific Confluence page by its ID.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `pageId` (`string`, required): The numeric ID of the Confluence page. Use getConfluenceSpaces or search to find page IDs.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `html`, `markdown`, `adf`.
- `contentType` (`string`, optional): Type of Confluence content: page, blogpost, or custom. One of: `page`, `blog`. Default: `page`.

Example input: `{"cloudId":"<cloudId>","pageId":"<pageId>"}`

### `atlassianmcp_getconfluencepagedescendants`

GetConfluencePageDescendants · Read-only

List all pages nested under a Confluence page, up to a specified depth.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `pageId` (`string`, required): Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw)
- `cursor` (`string`, optional): Pagination cursor
- `depth` (`number`, optional): Max depth
- `limit` (`number`, optional): Max descendants

Example input: `{"cloudId":"<cloudId>","pageId":"<pageId>"}`

### `atlassianmcp_getconfluencepagefootercomments`

GetConfluencePageFooterComments · Read-only

List footer comments on a Confluence page, optionally including replies.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `pageId` (`string`, required): Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw)
- `contentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.
- `contentType` (`string`, optional): Type of content: page or blog post. One of: `page`, `blog`. Default: `page`.
- `cursor` (`string`, optional): Pagination cursor
- `includeReplies` (`boolean`, optional): When true, also return reply comments. Default: `false`.
- `limit` (`number`, optional): Max comments
- `repliesPerComment` (`integer`, optional): No description.
- `sort` (`string`, optional): Sort order. One of: `id`, `-id`, `created-date`, `-created-date`.
- `status` (`string`, optional): Comment status. One of: `current`, `archived`, `trashed`, `deleted`, `historical`, `draft`. Default: `current`.

Example input: `{"cloudId":"<cloudId>","pageId":"<pageId>"}`

### `atlassianmcp_getconfluencepageinlinecomments`

GetConfluencePageInlineComments · Read-only

List inline comments on a Confluence page, optionally filtered by resolution status.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `pageId` (`string`, required): Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw)
- `contentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.
- `contentType` (`string`, optional): Type of content: page or blog post. One of: `page`, `blog`. Default: `page`.
- `cursor` (`string`, optional): Pagination cursor
- `includeReplies` (`boolean`, optional): When true, also return reply comments. Default: `false`.
- `limit` (`number`, optional): Max comments
- `repliesPerComment` (`integer`, optional): No description.
- `resolutionStatus` (`string`, optional): Resolution status. One of: `resolved`, `open`, `dangling`, `reopened`. Default: `open`.
- `sort` (`string`, optional): Sort order. One of: `id`, `-id`, `created-date`, `-created-date`.
- `status` (`string`, optional): Comment status. One of: `current`, `archived`, `trashed`, `deleted`, `historical`, `draft`. Default: `current`.

Example input: `{"cloudId":"<cloudId>","pageId":"<pageId>"}`

### `atlassianmcp_getconfluencespaces`

GetConfluenceSpaces · Read-only

List Confluence spaces accessible to the authenticated user, with optional filters.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `expand` (`string`, optional): Comma-separated list of fields to expand in the response.
- `favoritedBy` (`string`, optional): Return spaces favourited by this user account ID.
- `favourite` (`boolean`, optional): Set to true to return only spaces marked as favourite.
- `ids` (`string`, optional): List of space IDs to filter by.
- `keys` (`string`, optional): List of space keys to filter by.
- `labels` (`string`, optional): List of space labels to filter by.
- `limit` (`number`, optional): Maximum number of items to return.
- `start` (`number`, optional): Index of the first result for pagination (defaults to 0).
- `status` (`string`, optional): Filter by content status (e.g. current, archived, trashed). One of: `current`, `archived`.
- `type` (`string`, optional): Space type filter (e.g. global or personal). One of: `global`, `personal`.

Example input: `{"cloudId":"<cloudId>"}`

### `atlassianmcp_getissuelinktypes`

GetIssueLinkTypes · Read-only

List all available issue link types in a Jira instance (e.g. Blocks, Relates, Duplicate).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.

Example input: `{"cloudId":"<cloudId>"}`

### `atlassianmcp_getjiraissue`

GetJiraIssue · Read-only

Retrieve the details of a specific Jira issue by its ID or key.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `issueIdOrKey` (`string`, required): Issue ID or key (e.g., PROJ-123 or 10000)
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `expand` (`string`, optional): Additional issue details to expand in the response (for example, renderedFields or names).
- `failFast` (`boolean`, optional): Whether to fail quickly when some fields cannot be loaded instead of partially returning data.
- `fields` (`array`, optional): 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.
- `fieldsByKeys` (`boolean`, optional): Whether fields in the request are referenced by field keys instead of IDs.
- `properties` (`array`, optional): Issue property keys to include in the response.
- `responseContentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.
- `updateHistory` (`boolean`, optional): Whether to update the user's recently viewed projects/history for this issue request.

Example input: `{"cloudId":"<cloudId>","issueIdOrKey":"<issueIdOrKey>"}`

### `atlassianmcp_getjiraissueremoteissuelinks`

GetJiraIssueRemoteIssueLinks · Read-only

List remote links (external resources) attached to a Jira issue.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `issueIdOrKey` (`string`, required): The Jira issue ID (e.g. 10001) or key (e.g. KAN-1).
- `globalId` (`string`, optional): Optional global ID to filter remote issue links.

Example input: `{"cloudId":"<cloudId>","issueIdOrKey":"<issueIdOrKey>"}`

### `atlassianmcp_getjiraissuetypemetawithfields`

GetJiraIssueTypeMetaWithFields · Read-only

Retrieve field metadata for a specific Jira issue type in a project.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `issueTypeId` (`string`, required): The ID of the Jira issue type. Use getJiraProjectIssueTypesMetadata to list available types.
- `projectIdOrKey` (`string`, required): The Jira project ID or key (e.g. KAN or 10000). Use getVisibleJiraProjects to find it.
- `maxResults` (`number`, optional): Maximum number of results to return per page.
- `requiredFieldsOnly` (`boolean`, optional): 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).
- `startAt` (`number`, optional): Index of the first result to return (for pagination, defaults to 0).

Example input: `{"cloudId":"<cloudId>","issueTypeId":"<issueTypeId>","projectIdOrKey":"<projectIdOrKey>"}`

### `atlassianmcp_getjiraprojectissuetypesmetadata`

GetJiraProjectIssueTypesMetadata · Read-only

List all issue types and their field metadata for a Jira project.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `projectIdOrKey` (`string`, required): The Jira project ID or key (e.g. KAN or 10000). Use getVisibleJiraProjects to find it.
- `maxResults` (`number`, optional): Maximum number of results to return per page. Default: `50`.
- `startAt` (`number`, optional): Index of the first result to return (for pagination, defaults to 0). Default: `0`.

Example input: `{"cloudId":"<cloudId>","projectIdOrKey":"<projectIdOrKey>"}`

### `atlassianmcp_getpagesinconfluencespace`

GetPagesInConfluenceSpace · Read-only

List all pages in a Confluence space, optionally filtered by title or status.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `spaceId` (`string`, required): The numeric ID of the Confluence space. Use getConfluenceSpaces to list available spaces.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.
- `contentType` (`string`, optional): Type of Confluence content: page, blogpost, or custom. One of: `page`, `blog`. Default: `page`.
- `cursor` (`string`, optional): Cursor string for paginating through results.
- `limit` (`integer`, optional): Max results (default: 25, max: 250).
- `sort` (`string`, optional): Sort order for results (e.g. created-date, -modified, title). One of: `id`, `-id`, `created-date`, `-created-date`, `modified-date`, `-modified-date`, `title`, `-title`.
- `status` (`string`, optional): Filter by content status (e.g. current, archived, trashed). One of: `current`, `archived`, `deleted`, `trashed`.
- `title` (`string`, optional): The title of the Confluence page.

Example input: `{"cloudId":"<cloudId>","spaceId":"131073"}`

### `atlassianmcp_getteamworkgraphcontext`

GetTeamworkGraphContext · Read-only

Retrieve the teamwork graph context for an Atlassian object, showing related work across Jira, Confluence, and Compass.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `objectIdentifier` (`string`, required): Identifier for the object — an issue key (e.g. KAN-4), ARI, or URL.
- `objectType` (`string`, required): Type of the Atlassian object (e.g. JiraWorkItem, ConfluencePage, ConfluenceSpace, AtlassianUser, CompassComponent). One of: `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`.
- `after` (`string`, optional): Cursor for fetching the next page of results.
- `detailLevel` (`string`, optional): Level of detail to return for related objects (FULL or MINIMAL). One of: `summary`, `full`. Default: `summary`.
- `first` (`integer`, optional): Number of items to return in this page. Default: `50`.
- `relationshipTypes` (`array`, optional): Filter by specific relationship types (e.g. DEPENDS_ON, BLOCKED_BY).
- `targetObjectTypes` (`array`, optional): Filter related objects by type (e.g. JiraWorkItem, ConfluencePage).
- `timeRange` (`object`, optional): Optional time range filter as JSON: {"from": "<ISO8601>", "to": "<ISO8601>"}.

Example input: `{"cloudId":"<cloudId>","objectIdentifier":"<objectIdentifier>","objectType":"AtlassianGoal"}`

### `atlassianmcp_getteamworkgraphobject`

GetTeamworkGraphObject · Read-only

Hydrate one or more Atlassian objects from their URLs or ARIs to get their current state.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `objects` (`array`, required): List of object URLs or ARIs to hydrate (e.g. https://site.atlassian.net/browse/KAN-1).

Example input: `{"cloudId":"<cloudId>","objects":[]}`

### `atlassianmcp_gettransitionsforjiraissue`

GetTransitionsForJiraIssue · Read-only

List all available workflow transitions for a Jira issue, used before calling transitionJiraIssue.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `issueIdOrKey` (`string`, required): Issue ID or key (e.g., PROJ-123 or 10000)
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `expand` (`string`, optional): No description.
- `includeUnavailableTransitions` (`boolean`, optional): No description.
- `skipRemoteOnlyCondition` (`boolean`, optional): No description.
- `sortByOpsBarAndStatus` (`boolean`, optional): No description.
- `transitionId` (`string`, optional): No description.

Example input: `{"cloudId":"<cloudId>","issueIdOrKey":"<issueIdOrKey>"}`

### `atlassianmcp_getvisiblejiraprojects`

GetVisibleJiraProjects · Read-only

List Jira projects visible to the authenticated user, with optional search filtering.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `action` (`string`, optional): The action to filter projects by (e.g. browse, create). One of: `view`, `browse`, `edit`, `create`. Default: `create`.
- `expandIssueTypes` (`boolean`, optional): Set to true to include issue type details in the project list response. Default: `true`.
- `maxResults` (`number`, optional): Maximum number of results to return per page. Default: `50`.
- `searchString` (`string`, optional): Text to search for when looking up Jira users.
- `startAt` (`number`, optional): Index of the first result to return (for pagination, defaults to 0). Default: `0`.

Example input: `{"cloudId":"<cloudId>"}`

### `atlassianmcp_lookupjiraaccountid`

LookupJiraAccountId · Read-only

Search for Atlassian user accounts by name or email to find their account IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `searchString` (`string`, required): No description.
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `showAvatar` (`boolean`, optional): No description.

Example input: `{"cloudId":"<cloudId>","searchString":"<searchString>"}`

### `atlassianmcp_search`

Search · Read-only

Search across all Atlassian products (Jira and Confluence) using a keyword query.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): Search query to find Atlassian content across Jira and Confluence.
- `cloudId` (`string`, optional): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.

Example input: `{"query":"<query>"}`

### `atlassianmcp_searchconfluenceusingcql`

SearchConfluenceUsingCql · Read-only

Search Confluence content using Confluence Query Language (CQL).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `cql` (`string`, required): Confluence Query Language string (e.g. type = page AND space = SD AND title ~ "meeting").
- `cqlcontext` (`string`, optional): Optional JSON object to restrict CQL scope (e.g. {"spaceKey": "SD"}).
- `cursor` (`string`, optional): Cursor string for paginating through results.
- `expand` (`string`, optional): Comma-separated list of fields to expand in the response.
- `limit` (`number`, optional): Maximum number of items to return.
- `next` (`boolean`, optional): Include next page link
- `prev` (`boolean`, optional): Include previous page link

Example input: `{"cloudId":"<cloudId>","cql":"<cql>"}`

### `atlassianmcp_searchjiraissuesusingjql`

SearchJiraIssuesUsingJql · Read-only

Search for Jira issues using Jira Query Language (JQL).

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `jql` (`string`, required): JQL query
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `fields` (`array`, optional): 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.
- `maxResults` (`number`, optional): Max (50-100)
- `nextPageToken` (`string`, optional): Page token
- `responseContentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.
- `searchResultMode` (`string`, optional): 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. One of: `issues`, `count`, `all`.

Example input: `{"cloudId":"<cloudId>","jql":"<jql>"}`

### `atlassianmcp_addcommenttojiraissue`

AddCommentToJiraIssue · Write

Add a comment to an existing Jira issue, or update an existing comment by passing its commentId.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `commentBody` (`string`, required): The text content of the comment to add.
- `issueIdOrKey` (`string`, required): The Jira issue ID (e.g. 10001) or key (e.g. KAN-1).
- `commentId` (`string`, optional): ID of an existing comment to update. If omitted, a new comment is added.
- `commentVisibility` (`object`, optional): Restrict comment visibility as JSON (e.g. {"type": "role", "value": "Dev Team"}).
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.
- `responseContentFormat` (`string`, optional): Format to return content in — markdown (default) or adf. One of: `markdown`, `adf`.

Example input: `{"cloudId":"<cloudId>","commentBody":"<commentBody>","issueIdOrKey":"<issueIdOrKey>"}`

### `atlassianmcp_addworklogtojiraissue`

AddWorklogToJiraIssue · Write

Log time spent on a Jira issue by adding a worklog entry.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `issueIdOrKey` (`string`, required): The Jira issue ID (e.g. 10001) or key (e.g. KAN-1).
- `timeSpent` (`string`, required): Time spent on the issue, in Jira duration format (e.g. 1h, 2h 30m, 1d).
- `commentBody` (`string`, optional): The text content of the comment to add.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.
- `started` (`string`, optional): The date and time the work started, in ISO 8601 format (e.g. 2026-05-15T10:00:00.000+0000).
- `visibility` (`object`, optional): Restrict worklog visibility as JSON (e.g. {"type": "role", "value": "Dev Team"}).
- `worklogId` (`string`, optional): The ID of an existing worklog entry to update.

Example input: `{"cloudId":"<cloudId>","issueIdOrKey":"<issueIdOrKey>","timeSpent":"<timeSpent>"}`

### `atlassianmcp_createcompasscomponent`

CreateCompassComponent · Write

Create a new component in Atlassian Compass (e.g. a service, library, or application).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `name` (`string`, required): Name of the Compass component.
- `typeId` (`string`, required): Type ID of the Compass component (e.g. SERVICE, LIBRARY, APPLICATION).
- `description` (`string`, optional): The full description of the Jira issue.
- `labels` (`array`, optional): List of space labels to filter by.
- `ownerId` (`string`, optional): Atlassian account ID of the component owner.

Example input: `{"cloudId":"<cloudId>","name":"<name>","typeId":"<typeId>"}`

### `atlassianmcp_createcompasscomponentrelationship`

CreateCompassComponentRelationship · Write

Create a dependency or relationship between two Compass components.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `fromComponentId` (`string`, required): The ID of the source Compass component in the relationship.
- `relationshipType` (`string`, required): The type of relationship between components (e.g. DEPENDS_ON). One of: `DEPENDS_ON`, `DEPENDENCY_OF`.
- `toComponentId` (`string`, required): The ID of the target Compass component in the relationship.

Example input: `{"cloudId":"<cloudId>","fromComponentId":"<fromComponentId>","relationshipType":"DEPENDS_ON","toComponentId":"<toComponentId>"}`

### `atlassianmcp_createcompasscustomfielddefinition`

CreateCompassCustomFieldDefinition · Write

Define a new custom field for Compass components in your workspace.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `input` (`object`, required): Custom field definition as JSON (fields: name, type, description).

Example input: `{"cloudId":"<cloudId>","input":{}}`

### `atlassianmcp_createconfluencefootercomment`

CreateConfluenceFooterComment · Write

Add a footer comment to a Confluence page, blog post, or other content.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `body` (`string`, required): The body content of the Confluence page or comment, in the format specified by contentFormat.
- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `attachmentId` (`string`, optional): The ID of the attachment to comment on.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `html`, `markdown`, `adf`.
- `contentType` (`string`, optional): Type of Confluence content: page, blogpost, or custom. One of: `page`, `blog`. Default: `page`.
- `customContentId` (`string`, optional): The ID of the custom content to comment on.
- `pageId` (`string`, optional): The numeric ID of the Confluence page. Use getConfluenceSpaces or search to find page IDs.
- `parentCommentId` (`string`, optional): Optional ID of the parent comment, for creating a reply.

Example input: `{"body":"<body>","cloudId":"<cloudId>"}`

### `atlassianmcp_createconfluenceinlinecomment`

CreateConfluenceInlineComment · Write

Add an inline comment anchored to selected text on a Confluence page.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `body` (`string`, required): The body content of the Confluence page or comment, in the format specified by contentFormat.
- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `html`, `markdown`, `adf`.
- `contentType` (`string`, optional): Type of Confluence content: page, blogpost, or custom. One of: `page`, `blog`. Default: `page`.
- `inlineCommentProperties` (`object`, optional): Inline comment anchor as JSON: {"textSelection": "<text>", "textSelectionMatchCount": N, "textSelectionMatchIndex": N}.
- `pageId` (`string`, optional): The numeric ID of the Confluence page. Use getConfluenceSpaces or search to find page IDs.
- `parentCommentId` (`string`, optional): Optional ID of the parent comment, for creating a reply.

Example input: `{"body":"<body>","cloudId":"<cloudId>"}`

### `atlassianmcp_createconfluencepage`

CreateConfluencePage · Write

Create a new Confluence page in a space, optionally nested under a parent page.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `body` (`string`, required): The body content of the Confluence page or comment, in the format specified by contentFormat.
- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `spaceId` (`string`, required): The numeric ID of the Confluence space. Use getConfluenceSpaces to list available spaces.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `html`, `markdown`, `adf`.
- `contentType` (`string`, optional): Type of Confluence content: page, blogpost, or custom. One of: `page`, `blog`. Default: `page`.
- `isPrivate` (`boolean`, optional): Set to true to create the page as private (only visible to the creator).
- `parentId` (`string`, optional): The ID of the parent page under which to create or move this page.
- `status` (`string`, optional): Filter by content status (e.g. current, archived, trashed). One of: `current`, `draft`. Default: `current`.
- `subtype` (`string`, optional): Confluence page subtype (e.g. live for live pages). One of: `live`.
- `title` (`string`, optional): The title of the Confluence page.

Example input: `{"body":"<body>","cloudId":"<cloudId>","spaceId":"131073"}`

### `atlassianmcp_createissuelink`

CreateIssueLink · Write

Link two Jira issues together with a relationship type (e.g. Relates, Blocks, Duplicate).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `inwardIssue` (`string`, required): The key of the inward issue in the link (e.g. KAN-1).
- `outwardIssue` (`string`, required): The key of the outward issue in the link (e.g. KAN-2).
- `type` (`string`, required): Space type filter (e.g. global or personal).
- `comment` (`string`, optional): An optional comment to attach to the issue link.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.

Example input: `{"cloudId":"<cloudId>","inwardIssue":"<inwardIssue>","outwardIssue":"<outwardIssue>","type":"<type>"}`

### `atlassianmcp_createjiraissue`

CreateJiraIssue · Write

Create a new Jira issue in a project with the specified summary, type, and optional fields.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `cloudId` (`string`, required): The cloud site ID (UUID) of your Atlassian instance. Use getAccessibleAtlassianResources to retrieve it.
- `issueTypeName` (`string`, required): The name of the Jira issue type (e.g. Task, Story, Bug, Epic).
- `projectKey` (`string`, required): The Jira project key (e.g. KAN). Use getVisibleJiraProjects to list available projects.
- `summary` (`string`, required): A short summary of the Jira issue (the issue title).
- `additional_fields` (`object`, optional): Additional Jira fields to set on creation, as a JSON object (e.g. priority, labels).
- `assignee_account_id` (`string`, optional): Atlassian account ID of the user to assign. Use lookupJiraAccountId to find account IDs.
- `contentFormat` (`string`, optional): Format of the content body — use markdown for plain text or adf for Atlassian Document Format (JSON). One of: `markdown`, `adf`.
- `description` (`string`, optional): 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".
- `parent` (`string`, optional): The parent issue key (e.g. KAN-1) for creating subtasks or child issues.
- `responseContentFormat` (`string`, optional): Format to return content in — markdown (default) or adf. One of: `markdown`, `adf`.
- `transition` (`object`, optional): The transition to perform, as JSON: {"id": "<transition_id>"}. Use getTransitionsForJiraIssue to list valid transitions.

Example input: `{"cloudId":"<cloudId>","issueTypeName":"<issueTypeName>","projectKey":"<projectKey>","summary":"<summary>"}`

### `atlassianmcp_editjiraissue`

EditJiraIssue · Write

Update fields on an existing Jira issue, such as summary, priority, or description.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `fields` (`object`, required): 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.
- `issueIdOrKey` (`string`, required): Issue ID or key (e.g., PROJ-123 or 10000)
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `contentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.
- `responseContentFormat` (`string`, optional): 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. One of: `markdown`, `adf`.

Example input: `{"cloudId":"<cloudId>","fields":{},"issueIdOrKey":"<issueIdOrKey>"}`

### `atlassianmcp_getcontentformatguide`

Get Content Format Guide · Write

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.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `toolName` (`string`, required): The Confluence page tool whose body you are authoring: `createConfluencePage` or `updateConfluencePage`. Do not pass a content type or `getContentFormatGuide` itself.
- `reference` (`string`, optional): Forward-compatible provider-specific path for follow-up guidance referenced by the initial response. The current page guide does not emit follow-up references.

Example input: `{"toolName":"<toolName>"}`

### `atlassianmcp_transitionjiraissue`

TransitionJiraIssue · Write

Move a Jira issue to a new workflow status using a transition ID.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `issueIdOrKey` (`string`, required): Issue ID or key (e.g., PROJ-123 or 10000)
- `transition` (`object`, required): No description.
- `actionSource` (`string`, optional): Invocation attribution. Set to jira_mcp_card when called from a Jira MCP Widget UI; omit or set to model_tool_call for model/tool-loop calls. One of: `jira_mcp_card`, `model_tool_call`.
- `fields` (`object`, optional): No description.
- `historyMetadata` (`object`, optional): No description.
- `update` (`object`, optional): No description.

Example input: `{"cloudId":"<cloudId>","issueIdOrKey":"<issueIdOrKey>","transition":{}}`

### `atlassianmcp_updateconfluencepage`

UpdateConfluencePage · Write

Update the title, body, or other properties of an existing Confluence page.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `body` (`string`, required): Replacement page body. When contentFormat is "html" or omitted, author this field using the HTML-format guidance returned by the getContentFormatGuide tool for updateConfluencePage.
- `cloudId` (`string`, required): Cloud ID (UUID or site URL)
- `pageId` (`string`, required): Page or blog post ID, or a Confluence tiny link ID (the encoded part from /wiki/x/ URLs, e.g., Fc1bBw)
- `contentFormat` (`string`, optional): 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. One of: `html`, `markdown`, `adf`.
- `contentType` (`string`, optional): Type of content: page or blog post. One of: `page`, `blog`. Default: `page`.
- `includeBody` (`boolean`, optional): If true, include the page body in the response; if false, omit it to reduce payload size. Default: `false`.
- `parentId` (`string`, optional): ID of the parent to move the page under. Accepts the ID of any container that can hold a page â a page, folder, whiteboard, database, embed, or slide (smart links surface as embeds). Applies to pages only; ignored for blog posts.
- `spaceId` (`string`, optional): 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.
- `status` (`string`, optional): Page status. One of: `current`, `draft`. Default: `current`.
- `title` (`string`, optional): New title
- `versionMessage` (`string`, optional): Version message

Example input: `{"body":"<body>","cloudId":"<cloudId>","pageId":"<pageId>"}`

## Workflows

### Get your cloud ID

Most Atlassian Rovo MCP tools require a `cloudId` — the UUID that identifies your Atlassian cloud site. Call `atlassianmcp_getaccessibleatlassianresources` once to retrieve it, then pass the `id` field value in every subsequent tool call.

> note: Call this tool first
>
> Run `atlassianmcp_getaccessibleatlassianresources` before calling any Jira or Confluence tool. The response lists every Atlassian site the user has access to. Use the `id` field as `cloudId`.

  **Node.js**

  ```typescript
  // Step 1 — get the cloud ID
  const resources = await actions.executeTool({
    connector: 'atlassianmcp',
    identifier: 'user_123',
    toolName: 'atlassianmcp_getaccessibleatlassianresources',
    toolInput: {},
  });
  const cloudId = resources[0].id;

  // Step 2 — use cloudId in subsequent calls
  const issue = await actions.executeTool({
    connector: 'atlassianmcp',
    identifier: 'user_123',
    toolName: 'atlassianmcp_getjiraissue',
    toolInput: {
      cloudId,
      issueIdOrKey: 'KAN-1',
    },
  });
  console.log(issue);
  ```

  **Python**

  ```python
  # Step 1 — get the cloud ID
  resources = actions.execute_tool(
      connection_name="atlassianmcp",
      identifier="user_123",
      tool_name="atlassianmcp_getaccessibleatlassianresources",
      tool_input={},
  )
  cloud_id = resources[0]["id"]

  # Step 2 — use cloud_id in subsequent calls
  issue = actions.execute_tool(
      connection_name="atlassianmcp",
      identifier="user_123",
      tool_name="atlassianmcp_getjiraissue",
      tool_input={
          "cloudId": cloud_id,
          "issueIdOrKey": "KAN-1",
      },
  )
  print(issue)
  ```

The `atlassianmcp_getaccessibleatlassianresources` response looks like this:

```json
[
  {
    "id": "a4c9b3e2-1234-5678-abcd-ef0123456789",
    "name": "My Company",
    "url": "https://mycompany.atlassian.net",
    "scopes": ["read:jira-work", "write:jira-work", "read:confluence-content.all"]
  }
]
```

Use `id` as the `cloudId` parameter. If the user belongs to multiple Atlassian sites, the list contains one entry per site — pick the one matching the target `url`.

## Related

Other Project Management connectors ([all 40](/agentkit/connectors/?category=project-management)):

- [Notion](/agentkit/connectors/notion/): Scalekit connector, OAuth, 51 tools
- [Linear](/agentkit/connectors/linear/): Scalekit connector, OAuth, 62 tools
- [Airtable](/agentkit/connectors/airtable/): Scalekit connector, OAuth, 26 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
