Skip to main content
Glama

Atlassian MCP Server

MCP server that lets AI assistants interact with Jira through the Atlassian CLI.

Quick Start

See QUICKSTART.md for installation and setup.

Related MCP server: JIRA MCP Server

Features

✅ Search issues with JQL queries
✅ View full issue details
✅ Add comments
✅ Update status/transitions
✅ Assign to users
✅ Manage labels and custom fields
✅ Link related issues

How It Works

The MCP server calls the Atlassian CLI (acli) commands:

  1. AI assistant calls an MCP tool (e.g., jira_search)

  2. MCP server executes corresponding acli command

  3. Results are parsed and returned to the AI

Prerequisites

  • Node.js 18+

  • Atlassian CLI: winget install Atlassian.AtlassianCli

  • Authenticated Jira account: acli jira auth login

Available Tools

Tool

Description

jira_search

Search with JQL queries

jira_get_issue

Get issue details

jira_comment

Add comments

jira_update_status

Change status

jira_assign

Assign to user

jira_set_field

Update custom fields

jira_add_label

Add labels

jira_remove_label

Remove labels

jira_link_issue

Link issues

Usage Example

Ask your AI assistant:

  • "Find my open work items"

  • "Add a comment to PROJ-123"

  • "Show high priority issues"

  • "Move PROJ-456 to In Progress"

The AI will automatically use the appropriate MCP tools.

Development

npm install     # Install dependencies
npm run build   # Build TypeScript
npm run watch   # Auto-rebuild on changes
npm start       # Run the server

Available Tools

9 tools
jira_add_labelA

Add a label/tag to a Jira work item. Use to categorize and organize work items for easier filtering and tracking.

Inputs: issue_key (required), label (required).

jira_assignB

Assign a Jira work item to a user. Use to delegate tasks and clarify ownership of work items.

Inputs: issue_key (required), assignee (required).

jira_commentA

Add a comment to a Jira work item. Use to provide status updates, ask questions, or share information with the team working on the issue.

Inputs: issue_key (required), comment (required).

jira_get_issueA

Retrieve detailed information about a specific Jira work item. Shows all fields including description, reporter, watchers, attachments, linked issues, and full history.

Inputs: issue_key (required).

jira_remove_labelB

Remove a label/tag from a Jira work item. Use to clean up or reorganize issue categorization.

Inputs: issue_key (required), label (required).

jira_set_fieldB

Update a custom field value on a Jira work item. Use to set fields like components, fix versions, labels, environment, etc.

Inputs: issue_key (required), field (required), value (required).

jira_update_statusB

Transition a Jira work item to a new status (e.g., 'In Progress', 'Done', 'Blocked'). Use to move work items through your workflow.

Inputs: issue_key (required), status (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 9 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific Jira operations with no overlap. For example, jira_add_label and jira_remove_label are complementary but distinct, while jira_get_issue, jira_search, and jira_update_status each handle different aspects of issue management. The descriptions reinforce these boundaries, making misselection unlikely.

    Naming Consistency5/5

    All tools follow a consistent 'jira_verb_noun' pattern using snake_case throughout. The verbs are specific and descriptive (e.g., add, assign, comment, get, link, remove, search, set, update), creating a predictable and readable naming convention across the entire set.

    Tool Count5/5

    With 9 tools, the server is well-scoped for Jira operations, covering core workflows without bloat. Each tool earns its place by addressing a specific need in issue management, from retrieval and search to updates and relationships, making the count appropriate for the domain.

    Completeness4/5

    The toolset provides strong coverage for common Jira workflows, including CRUD-like operations (get, search, update status, set fields), collaboration (comment, assign), and organization (labels, links). A minor gap exists in missing explicit create or delete issue tools, but agents can work around this using jira_set_field or other methods for creation, and the surface otherwise supports most agent tasks effectively.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers