Skip to content

Summary

Community MCP server for Jira and Confluence with 98 tools, supporting both Atlassian Cloud and self-managed Server/Data Center.

Features

  • 98 tools across Jira and Confluence
  • JQL and CQL search, issue transitions, page creation and comments
  • Works with Atlassian Cloud and Server/Data Center
  • API token, personal access token or OAuth 2.0 auth
  • stdio, SSE and streamable-HTTP transports

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it, filling in the environment variables with your own values.
  3. Restart the agent — the "MCP Atlassian" tools will be available.
{
  "mcpServers": {
    "mcp-atlassian": {
      "command": "uvx",
      "args": [
        "mcp-atlassian"
      ],
      "env": {
        "JIRA_URL": "https://your-company.atlassian.net",
        "JIRA_USERNAME": "your.email@company.com",
        "JIRA_API_TOKEN": "your_api_token",
        "CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
        "CONFLUENCE_USERNAME": "your.email@company.com",
        "CONFLUENCE_API_TOKEN": "your_api_token"
      }
    }
  }
}

Description

MCP Atlassian is a widely used open-source MCP server that gives AI assistants read and write access to Jira and Confluence. Ask it to "find issues assigned to me in PROJ", "create a bug ticket for the login issue", "move PROJ-123 to Done" or "search Confluence for onboarding docs" and it runs the matching JQL or CQL queries and API calls; 98 tools cover issue search, creation, updates and transitions, and page search, reading, creation, updates and comments.

Its main difference from Atlassian's own hosted Rovo MCP server is deployment coverage: besides Cloud it supports Jira Server and Data Center 8.14+ and Confluence Server and Data Center 6.0+, authenticating with API tokens, personal access tokens or OAuth 2.0. It runs locally from PyPI with uvx, or via Docker or pip, over stdio by default, with SSE and streamable-HTTP transports for multi-user deployments.

Documentation lives at mcp-atlassian.soomiles.com and is also published as llms.txt. MIT licensed; not an official Atlassian product.

MCP: Engram

by Gentleman Programming

Featured

Persistent memory for coding agents as a single Go binary — SQLite and FTS5 behind MCP, an HTTP API, a CLI and a TUI, with no Node, Python or Docker required.

MCP: OKF Agent Memory

by okf-memory

Git-native persistent memory for coding agents — sub-300µs BM25 search over version-controlled plain text, with no embeddings, no database and no API costs.

MCP: Memory

by Model Context Protocol

A knowledge-graph-based persistent memory system that lets an agent remember entities and relations across sessions.

Nulab's official MCP server for Backlog — let an agent read and write projects, issues, comments, milestones, wiki pages, Git repositories and pull requests through the Backlog API.

Browse all MCP servers →