MCP Atlassian MCP Server

MCP Atlassian MCP server exists for a simple reason — assistants are far more useful when they can act on MCP Atlassian directly instead of describing what you should do. MCP server for Atlassian (Confluence & Jira).

What you get

A Model Context Protocol (MCP) server that provides comprehensive tools for interacting with Atlassian products (Confluence and Jira).

This MCP server allows AI agents to interact with Atlassian products through a standardized interface. It provides extensive tools for:

• Modern API Support — Uses Confluence v2 REST API with fallback to v1 for search functionality
• Comprehensive Toolset — 18+ Confluence tools and 8+ Jira tools covering all major operations
• Security & Privacy — Built-in PII filtering and SSL verification controls
• Flexible Configuration — Support for separate service URLs, authentication methods, and tool filtering
• Pagination Support — Cursor-based pagination for v2 APIs and offset/limit for v1 APIs
• Error Handling — Comprehensive error handling with detailed error messages

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once MCP Atlassian is connected, these are the calls the assistant has available:

• search_confluence — Search for content in Confluence using v1 API with CQL
• Parameters — searchText (string), spaceKey (string, optional), limit (number), start (number)
• search_confluence_pages_by_title — Search pages by title using v2 API
• get_confluence_space_by_id_or_key — Get information about a specific Confluence space
• get_confluence_spaces — Get all available spaces
• get_confluence_content — Get specific page content by ID
• get_confluence_pages — Get all pages in a space
• get_confluence_child_pages — Get child pages of a specific page
• confluence_create_page — Create a new Confluence page
• confluence_update_page — Update an existing page
• update_confluence_page_title — Update only the title of a page
• confluence_delete_page — Delete a Confluence page

Configuration and credentials

You will need 2 environment variables: ATLASSIAN_HOST, ATLASSIAN_API_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

• Node.js (v16 or higher) - npm or yarn - Atlassian account with API token - Docker (optional, for containerized deployment)

Before you rely on it

• Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
• With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Atlassian.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp atlassian mcp server does with a few real requests.

Choosing this one

Among the planning and project tracking options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP Atlassian's toolset — search_confluence, Parameters, search_confluence_pages_by_title and 11 more — is a fair guide to whether it matches your workflow. It is maintained by samwang0723; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.