How Wix scaled AI-native work to 5,000 employees with Willow
Read More
Enterprise Connectors
Atlassian v1 logo. Atlassian v1 MCP server connector.

Atlassian v1 MCP Server

Read and write Jira issues and Confluence pages through Atlassian's own MCP server (v1 endpoint).

ToolsTools
41
Last updatedLast Updated
✓Enterprise-grade security
✓SSO & authentication ready
✓Full governance & audit logs

What is the Atlassian v1 MCP Server?

The Atlassian v1 MCP server gives AI agents structured, permission-aware access to Atlassian v1 through the Model Context Protocol. With 41 pre-built actions, agents can read, create, and update Atlassian v1 data on behalf of authorized users.

Willow ships the Atlassian v1 MCP server as part of an enterprise control plane. Every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to a full audit trail, and integrates with Splunk and Loki for SIEM visibility. Connect from Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, or any custom agent. Install once, distribute org-wide, and see exactly how Atlassian v1 is being used by every AI agent in your stack.

Tools

atlassianUserInfo

Get current user info

getAccessibleAtlassianResources

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.

getContentFormatGuide

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.

getConfluencePage

Get a Confluence page or blog post by ID, including body content. Use getTeamworkGraphContext with objectType ConfluencePage, ConfluenceBlogPost, ConfluenceWhiteboard, or ConfluenceSpace to get linked comments, child pages, shared users, and page owners.

searchConfluenceUsingCql

Search Confluence content (pages, blog posts, comments, attachments) using CQL (Confluence Query Language). CQL is specific to Confluence and is not interchangeable with JQL.

getConfluenceSpaces

Get spaces

getPagesInConfluenceSpace

Get pages or blog posts in a space

getConfluencePageFooterComments

Get footer comments for a page or blog post

getConfluencePageInlineComments

Get inline comments for a page or blog post

getConfluenceCommentChildren

Get reply(child) comments for a comment

getConfluencePageDescendants

Get child pages of specified page

createConfluencePage

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".

updateConfluencePage

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".

createConfluenceFooterComment

Create a footer comment on a page or blog post

createConfluenceInlineComment

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.

getJiraIssue

Get issue details. Use getTeamworkGraphContext to get linked deployments, PRs, builds, branches, commits, designs, issues, confluence whiteboards, feature flags, vulnerabilities, sprints and remote links to Jira Issues.

editJiraIssue

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.

createJiraIssue

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).

getTransitionsForJiraIssue

Get transitions

getJiraIssueRemoteIssueLinks

Get remote links

getVisibleJiraProjects

Get projects

getJiraProjectIssueTypesMetadata

Get issue types

getJiraIssueTypeMetaWithFields

Get field metadata

addCommentToJiraIssue

Add or update a comment on a Jira issue

transitionJiraIssue

Transition issue status

searchJiraIssuesUsingJql

Search issues with JQL, total counts only when explicitly requested.

lookupJiraAccountId

Lookup user IDs

addWorklogToJiraIssue

Add or update a worklog on a Jira issue. When worklogId is provided, updates that worklog;

getIssueLinkTypes

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).

createIssueLink

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.

getCompassComponents

Get a list of Compass components

getCompassComponent

Get a Compass component by ID

getCompassCustomFieldDefinitions

Get a list of Compass custom field definitions

createCompassCustomFieldDefinition

Create a custom field definition in Compass

createCompassComponent

Create a new Compass component

createCompassComponentRelationship

Create a relationship between Compass components

getTeamworkGraphContext

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.

getTeamworkGraphObject

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.

addTeamworkGraphContext

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).

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.

fetch

Get a Jira issue or Confluence page by its ARI (Atlassian Resource Identifier). Only call this tool if your id is an ARI of the form "ari:cloud:jira:{cloudId}:issue/{id}" or "ari:cloud:confluence:{cloudId}:page/{id}". If it is not, do not call this tool — use another tool that accepts the identifier you have

Customize tools

Customize Tools

Edit descriptions, modify arguments, select tools, or add new ones

ReviewEdit descriptions
ConfigureChange arguments
ApproveSelect tools
Create NewAdd tool

Set Up Your Atlassian v1 MCP Server in Minutes

Add the following configuration to your MCP client. Authentication is handled via OAuth. Compatible with Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code, n8n, and any MCP-compatible agent.

Claude Desktop

claude_desktop_config.json
{
  "mcpServers": {
    "willow-atlassian-official-v1": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/atlassian-official-v1"
    }
  }
}

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "willow-atlassian-official-v1": {
      "type": "http",
      "url": "https://<org>.mcp-s.com/mcp/mcp/atlassian-official-v1"
    }
  }
}

Claude Code

CLI
claude mcp add willow-atlassian-official-v1 --transport http https://<org>.mcp-s.com/mcp/mcp/atlassian-official-v1

n8n

HTTP Request Node
{
  "url": "https://<org>.mcp-s.com/mcp/mcp/atlassian-official-v1",
  "method": "POST"
}

Or click "Install with Willow" above to set up automatically with SSO and RBAC preconfigured.

Enterprise Governance for Atlassian v1

Willow adds the layer Atlassian v1 and every other SaaS doesn't ship out of the box: every call runs behind SSO (Okta, Azure AD), enforces RBAC and least-privilege at runtime, writes to full audit logs, and detects shadow AI usage across your stack. One MCP gateway. Any agent. Every tool.

Atlassian v1 MCP Server FAQ

What is the Atlassian v1 MCP server?

The Atlassian v1 MCP server is a Model Context Protocol implementation that lets AI agents like Claude, Cursor, and ChatGPT read and write Atlassian v1 data through a standardized interface. Willow hosts and governs this server so enterprises can roll it out without a security review backlog.

How is Willow's Atlassian v1 MCP server different from the official one?

The official Atlassian v1 MCP server is scoped to a single user's account and does not include enterprise governance. Willow's version adds SSO, RBAC, audit logging, shadow AI detection, and centralized control over which actions agents can take across the entire org.

Which AI clients work with the Atlassian v1 MCP server?

Claude Desktop, Claude Code, Cursor, ChatGPT, VS Code with MCP support, n8n, and any custom agent built with OpenAI Agents SDK, LangChain, Vercel AI SDK, or Anthropic SDK.

Is the Atlassian v1 MCP server secure? How does Willow handle authentication?

Every call runs behind your existing SSO (Okta, Azure AD). Per-user OAuth scopes the agent to exactly what that user can do in Atlassian v1, nothing more. No credentials reach the LLM. Every action writes to an audit trail.

Can I limit which Atlassian v1 actions agents can take?

Yes. Willow lets you scope agents to specific actions, specific projects, or specific environments. Toggle actions on or off in the dashboard, or enforce policy via infrastructure-as-code through GitHub.

How do I detect shadow Atlassian v1 MCP servers in my org?

Willow's browser extension and discovery service surface unmanaged MCP servers, skills, and AI agents across the org. If a developer installed an unapproved Atlassian v1 MCP locally, you'll see it.

What does the Atlassian v1 MCP server cost?

Pricing depends on org size and deployment model (SaaS, dedicated cloud, self-host). See withwillow.ai/pricing or contact sales for a quote.

How do I install the Atlassian v1 MCP server with Willow?

Install via the Willow Connect Panel in one click, or paste the JSON snippet above into your Claude Desktop, Cursor, or Claude Code config. SSO and RBAC inherit from your existing Willow setup.

Compare Willow MCP Gateway

See how Willow stacks up against other MCP platforms on governance, security, and enterprise readiness.

Your agents are already in the wild.

Give them a Basecamp. Go from AI chaos to AI work, in minutes.