Name: MCP Atlassian Server
Author: petrsovadina

LABSCO SUMMARY

Two query languages, exposed honestly.

This does not try to wrap Atlassian in a friendly abstraction — it hands the assistant CQL and JQL and lets it write the query, which is the right call when the person asking already thinks in those terms. What it does not do is write: no issue creation, no transitions, no page edits, so it is safe to point at a production instance and useful mainly for finding and reading.

What it is

A small MCP server that puts Atlassian's two query languages in front of an assistant: CQL against Confluence content and JQL against Jira issues. It also registers resource templates so a page or an issue can be addressed directly by space and title, or by project and issue key.

What you get

Confluence content found by CQL query — pages, attachments and comments, filterable by space, with a result limit between 1 and 50 — confluence_search
Jira issues found by JQL query, with the field list you want returned (summary, status, assignee, timestamps) and the same 1 to 50 limit — jira_search
Direct addressing of a single item through resource templates: confluence://{space_key}/pages/{title} and jira://{project_key}/issues/{issue_key}

Requirements

An Atlassian account and an API token for each product you want reached. Confluence takes CONFLUENCE_URL, CONFLUENCE_USERNAME and CONFLUENCE_API_TOKEN; Jira takes JIRA_URL, JIRA_USERNAME and JIRA_API_TOKEN. The npm package name is mcp-confluence (1.0.0); clone, run npm install and npm run build, then point your client at build/index.js. MIT licensed.

Setup effort

Build from source — git clone https://github.com/petrsovadina/mcp-atlassian.git

See installation options

USE CASES

01

Finding the decision that was written down somewhere

Search Confluence with a CQL filter narrowed to one space, ordered by creation date, and read back the matching pages.

confluence_search

02

Pulling a work-in-progress list into a conversation

Run a JQL query for a project's open issues and ask for just summary, status and assignee so the answer stays readable.

jira_search

03

Cross-checking a ticket against its spec

Look up the issue by key, then search the space where its specification lives, in the same conversation.

jira_searchconfluence_search

2 tools

Listed in project docs. Your client may show a different list.

confluence_search

jira_search

BEFORE YOU INSTALL

What to know first

Tools you get

2 tools named in the project's documentation. Both tools only read; nothing writes to Confluence or Jira. The confluence:// and jira:// entries are resource templates, not tools.

Requires

node on PATH
CONFLUENCE_API_TOKEN in your environment
JIRA_API_TOKEN in your environment

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

You clone and build this one yourself.

Server setup

TERMINAL

git clone https://github.com/petrsovadina/mcp-atlassian.git
cd mcp-atlassian
npm install
npm run build

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "atlassian": {
      "command": "node",
      "args": [
        "<YOUR_PATH_TO_MCP_ATLASSIAN>/build/index.js"
      ],
      "env": {
        "CONFLUENCE_URL": "<YOUR_CONFLUENCE_URL>",
        "CONFLUENCE_USERNAME": "<YOUR_CONFLUENCE_USERNAME>",
        "CONFLUENCE_API_TOKEN": "<YOUR_CONFLUENCE_API_TOKEN>",
        "JIRA_URL": "<YOUR_JIRA_URL>",
        "JIRA_USERNAME": "<YOUR_JIRA_USERNAME>",
        "JIRA_API_TOKEN": "<YOUR_JIRA_API_TOKEN>"
      }
    }
  }
}

MCP Atlassian Server