MCP Server

Project ManagementIssue TrackingAPI Token Required

Jira MCP Server

by Community · Model Context Protocol for Atlassian Jira

Jira MCP Server gives your AI coding assistant direct access to Jira project management. Your agent can search issues with JQL, retrieve sprint backlogs, create new tickets, update fields, transition issues through workflow states, and add comments — all from Claude Code without opening the Jira UI or writing REST API calls manually.

Connect your development workflow end-to-end: agents can create Jira tickets from GitHub issues, update sprint status based on CI results, generate daily standup summaries from in-progress issues, and file bug reports automatically when monitoring detects anomalies — all driven by structured MCP tool calls.

JQL

Query Language

full Jira query support

Full CRUD

Operations

create, read, update, transition

API Token

Auth

Atlassian account token

Supported

Sprints

active + backlog access

Quick Install

claude mcp add jira -- npx jira-mcp-server

Key Features

JQL Issue Search

Search Jira issues using JQL — Jira's full-featured query language. Filter by project, status, assignee, priority, labels, fix version, created date, and custom fields. Retrieve paginated results with configurable field selection to limit response size.

Issue Creation

Create new issues with full field specification: project, issue type (Bug, Story, Task, Epic), summary, description, priority, assignee, labels, components, fix version, and custom fields. Useful for agents that automatically file bug reports, create tasks from monitoring alerts, or generate sprint tickets from requirements.

Issue Updates & Transitions

Update any writable field on existing issues and transition issues through workflow states (e.g., move from "Open" to "In Progress" or "In Review" to "Done"). Agents can update status as they work on tasks, keeping Jira in sync with actual progress without manual updates.

Sprint Information

List active and recent sprints for a board, retrieve sprint backlog items, and get sprint goal and velocity data. Useful for generating sprint status reports, identifying blocked issues, and monitoring sprint health throughout the development cycle.

Comment Management

Add comments to issues with formatted text, @mentions, and links. Retrieve existing comments for context before adding new ones. Agents can post progress updates, link related resources, or document decisions directly in the relevant Jira ticket as part of their workflow.

Project & Metadata

List accessible Jira projects, retrieve project configuration including issue types and workflows, and inspect field configurations and custom field metadata. Helps agents understand project structure before creating issues or constructing JQL queries.

Execution Brief

Use this page as a rollout checklist, not just reference text.

Suggest update

Tool Mapping Lens

Organize Tools by Workflow Phase

Catalog-oriented pages work best when users can map discovery, evaluation, and rollout in a clear path instead of reading an undifferentiated list.

Define the job-to-be-done first
Group tools by stage
Prioritize by adoption friction

Actionable Utility Module

Skill Implementation Board

Use this board for Jira MCP Server before rollout. Capture inputs, apply one decision rule, execute the checklist, and log outcome.

Input: Objective

Deliver one measurable improvement with jira mcp server claude code project management issues sprints jql atlassian agent

Input: Baseline Window

20-30 minutes

Input: Fallback Window

8-12 minutes

Decision Trigger	Action	Expected Output
Input: one workflow objective and release owner are defined	Run preview execution with fixed acceptance criteria.	Go or hold decision backed by repeatable evidence.
Input: output quality below baseline or retries increase	Limit scope, isolate root issue, and rerun controlled test.	One confirmed correction path before wider rollout.
Input: checks pass for two consecutive replay windows	Promote to broader traffic with fallback path active.	Stable rollout with low operational surprise.

Execution Steps

Record objective, owner, and stop condition.
Execute one controlled preview run.
Measure quality, latency, and correction burden.
Promote only when pass criteria are stable.

Output Template

tool=jira mcp server claude code project management issues sprints jql atlassian agent
objective=
preview_result=pass|fail
primary_metric=
next_step=rollout|patch|hold

Share execution feedback

What Is Jira MCP Server?

Jira MCP Server is a Model Context Protocol integration that gives AI coding assistants direct access to Atlassian Jira's issue tracking and project management platform. It exposes JQL search, issue CRUD operations, workflow transitions, sprint information, and comment management as MCP tools that agents can call from within Claude Code.

For most engineering teams, Jira is the authoritative record of what needs to be done, what's in progress, and what's blocked. Connecting agents to Jira closes a critical loop: instead of agents reasoning about work in isolation, they can read actual sprint state, create real tickets from their findings, and update issue status as they complete tasks — keeping the project management system in sync with agent activity.

Authentication uses an Atlassian API token combined with your Jira Cloud instance URL and email address. This gives the MCP server the same access as your user account. For production use, consider using a dedicated service account with permissions scoped to the projects the agent needs — this prevents agents from inadvertently accessing or modifying unrelated projects.

Jira MCP creates powerful connections across the development toolchain. Agents can detect a failing GitHub CI check, create a Jira bug report with the full error context, assign it to the responsible team, and post the Jira ticket link as a GitHub PR comment — all in one automated workflow. Sprint reporting, capacity planning, and velocity analysis become agent-driven tasks rather than manual data aggregation sessions.

How to Calculate Better Results with jira mcp server claude code project management issues sprints jql atlassian agent

Generate an Atlassian API token at id.atlassian.com/manage-profile/security/api-tokens. This token authenticates the MCP server as your Atlassian user account. Set three environment variables: JIRA_BASE_URL to your Jira Cloud URL (e.g., https://mycompany.atlassian.net), JIRA_EMAIL to your Atlassian account email, and JIRA_API_TOKEN to the generated token.

Install the Jira MCP server and register it with your AI client using the quick install command. Test the connection by asking your agent to list the Jira projects accessible to your account. If projects appear with their keys and names, authentication is working correctly.

Learn the JQL query patterns most relevant to your workflow. Start simple: "project = MYPROJECT AND status = 'In Progress'" to see current work. Gradually build more complex queries as you understand your project's field structure and workflow states. Ask the agent to inspect your project's issue types and available transitions before trying to create or transition issues.

For write operations, test on a sandbox project or a low-stakes issue first. Ask the agent to create a test issue, update a field, add a comment, and delete the test issue to confirm the full write lifecycle works before enabling agents to operate on production sprints.

Treat this page as a decision map. Build a shortlist fast, then run a focused second pass for security, ownership, and operational fit.

When a team keeps one shared selection rubric, tool adoption speeds up because evaluators stop debating criteria every time a new option appears.

Worked Examples

Automated bug filing from production monitoring

Your production monitoring detects an anomaly — error rate spike on a specific API endpoint — and you want a Jira bug filed automatically
The agent uses AWS MCP to pull CloudWatch error logs and identify the specific error type, affected endpoint, and frequency of occurrence
A Jira issue is created via Jira MCP with type Bug, priority High, a descriptive summary including the endpoint name, and a detailed description with error messages, timestamps, and CloudWatch log links
The issue is assigned to the team responsible for that API service based on a team ownership mapping the agent maintains
A comment is added with the raw CloudWatch query that surfaces the errors, so the assignee can immediately see the live data
The GitHub repository linked to the service is queried via GitHub MCP for recent commits to the affected area, and their authors are mentioned in the Jira comment

Outcome: A production incident automatically converted into a prioritized, well-documented Jira bug ticket with context, log links, and team assignment — filed within seconds of detection.

Daily sprint standup summary generation

You want a daily automated summary of sprint status to post in Slack before the morning standup
The agent queries Jira via JQL for all issues in the current active sprint: completed yesterday, in progress today, and blocked
For in-progress issues, the agent retrieves recent comments to understand current status and any blockers mentioned
Issues with no activity in the past 2 days are flagged as potentially stalled for the team to discuss
A standup summary is formatted: "Done: [list], In Progress: [list with notes], Blocked: [list with reasons], Stalled: [list]"
The summary is posted to the team Slack channel via Slack MCP with links to each Jira issue for one-click access

Outcome: An automated daily standup brief — actual sprint status with context, not a list of issue keys — delivered to Slack before the meeting starts so the team can review it asynchronously.

Frequently Asked Questions

What is the Jira MCP Server?

Jira MCP Server is a Model Context Protocol integration that connects AI coding assistants to Atlassian Jira's project management platform. It exposes tools for searching issues with JQL (Jira Query Language), creating new tickets, updating issue fields, transitioning issues through workflow states, adding comments, retrieving sprint information, and listing projects — all as MCP tool calls that Claude Code or any MCP-compatible client can invoke directly.

What Jira operations does the MCP server support?

Typical supported operations include: search_issues for JQL-based issue queries, get_issue for retrieving a specific issue by key, create_issue for creating new tickets with type, summary, description, priority, assignee, and labels, update_issue for modifying existing issue fields, transition_issue for moving issues through workflow states (e.g., "In Progress" to "In Review"), add_comment for posting comments on issues, get_project for project metadata, and list_sprints for active and recent sprint information.

Does Jira MCP work with both Jira Cloud and Jira Server/Data Center?

Most Jira MCP implementations support Jira Cloud (the hosted version at atlassian.net). Jira Server and Data Center use a different API version and base URL, so support varies by implementation. Check the specific MCP server's README to confirm which Jira deployment type is supported. For Jira Cloud, you authenticate with an API token generated from your Atlassian account. For Server/Data Center, PAT authentication is typically used.

How do I authenticate with Jira MCP?

For Jira Cloud, generate an API token at id.atlassian.com/manage-profile/security/api-tokens. Set three environment variables: JIRA_BASE_URL (your Atlassian domain, e.g., https://yourcompany.atlassian.net), JIRA_EMAIL (your Atlassian account email), and JIRA_API_TOKEN (the generated token). The server uses Basic auth combining your email and API token to authenticate API requests on your behalf.

Can the agent use JQL to search for issues?

Yes. The search_issues tool accepts JQL queries — Jira's SQL-like query language — giving agents powerful filtering. Common agent queries include: "project = MYPROJECT AND status = 'In Progress' AND assignee = currentUser()" to find in-progress work, "priority = High AND created >= -7d" to find recently created high-priority issues, or "fixVersion = '2.0' AND status != Done" to see what remains for a release. Agents that understand JQL can answer complex project status questions from a single tool call.

What are the common security considerations for Jira MCP?

Use a dedicated service account or your personal Atlassian API token scoped with minimal permissions. For read-only agent workflows (sprint monitoring, reporting), this is straightforward. For write operations, be careful about agents auto-creating or transitioning issues in production projects — always test in a sandbox project first. Jira API tokens have broad access to everything the user account can do, so consider using a restricted service account if your Jira instance supports permission-scoped tokens.

Missing a better tool match?

Send the exact workflow you are solving and we will prioritize a new comparison or rollout guide.

Submit feedback