Unified Atlassian Integration for MCP

This MCP server instance serves as a unified gateway for interacting with Atlassian ecosystems (Confluence documentation repositories and Jira issue tracking systems) directly through the Model Context Protocol interface.

Core Capabilities

Confluence Repository Access

• Execute granular searches leveraging the Confluence Query Language (CQL).
• Retrieve structured data pertaining to wiki pages, attached files, and associated commentary threads.
• Implement precise result scoping by filtering operations based on designated knowledge spaces.

Jira Issue Management

• Perform targeted ticket lookups utilizing the Jira Query Language (JQL).
• Obtain comprehensive issue attributes, such as resolution status, current assignment ownership, and timestamps of relevant events.

Deployment Procedures

Automated Installation via Smithery Client

For expedited setup targeting the Claude Desktop environment, employ the Smithery CLI:

bash npx -y @smithery/cli install @petrsovadina/mcp-atlassian --client claude

Manual Source Integration

For local or custom environment deployment:

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

Configuration Directives

Environment variables must be configured to establish connection credentials and endpoint locations:

Confluence Connection Parameters

CONFLUENCE_URL=https://your-domain.atlassian.net/wiki CONFLUENCE_USERNAME=your-email@domain.com CONFLUENCE_API_TOKEN=your-api-token

Jira Connection Parameters

JIRA_URL=https://your-domain.atlassian.net JIRA_USERNAME=your-email@domain.com JIRA_API_TOKEN=your-api-token

Integration within MCP Settings

Incorporate the following configuration block into your primary MCP configuration file to enable the server:

{ "mcpServers": { "atlassian": { "command": "node", "args": ["/path/to/mcp-atlassian/build/index.js"], "env": { "CONFLUENCE_URL": "your-confluence-url", "CONFLUENCE_USERNAME": "your-username", "CONFLUENCE_API_TOKEN": "your-api-token", "JIRA_URL": "your-jira-url", "JIRA_USERNAME": "your-username", "JIRA_API_TOKEN": "your-api-token" } } } }

Exposed Toolset

Tool: confluence_search

Performs data retrieval from Confluence archives using CQL syntax.

typescript { "query": "type=page AND space='Engineering' ORDER BY lastModified DESC", // CQL expression for content filtering "limit": 15 // Optional constraint on the maximum number of returned records (range: 1-50) }

Tool: jira_search

Executes issue lookups within Jira projects via JQL.

typescript { "jql": "project = ENG AND resolution = Unresolved", // JQL expression for issue identification "fields": "summary,priority,created,creator", // Selectively fetch required fields "limit": 20 // Optional constraint on the maximum number of returned records (range: 1-50) }

Resource Addressing Schemas

Confluence Content Locator

confluence://{space_key}/pages/{title_slug}

Jira Ticket Locator

jira://{project_key}/issues/{issue_key_identifier}

Usage Examples in Code

Querying Confluence Resources

typescript const confluenceData = await mcp.use('confluence_search', { query: "text ~ \"protocol specification\" AND type=page", limit: 10 });

Querying Jira Issues

typescript const jiraTickets = await mcp.use('jira_search', { jql: "project = SUPPORT AND priority = Highest", fields: "summary,status,assignee,updated", limit: 7 });

Contribution Guidelines

To participate in the ongoing enhancement of this component, please adhere to the following development workflow: 1. Initiate a fork of the primary repository. 2. Establish a dedicated feature branch for your modifications. 3. Commit your code changes with descriptive messages. 4. Push the developed branch to your fork. 5. Submit a formal Pull Request for review and integration.

Licensing Information

This software is distributed under the MIT License.