atlassian-mcp
The atlassian-mcp server integrates self-hosted Jira and Bitbucket with the Model Context Protocol (MCP), enabling AI-driven development workflows through natural-language interaction.
Workflow Tools
Get dev context: Returns current git branch state, linked Jira ticket overview, open PR with reviewer/blocker status, and next-step hints
Start work: Resolve a Jira ticket, create a local branch, fetch project README for conventions, and optionally transition the ticket
Complete work: Merge an open PR and transition the Jira ticket to Done in one step
Git Tools
Get git context: View branch, upstream ahead/behind, recent commits, working tree status, diff stat, and Jira keys in the branch name
Get git diff: Diff uncommitted changes or between two refs/commits, with paging support
Jira Tools
Search: Discover issues (text, JQL, project, status, assignee), projects, boards, sprints, fix versions, and users
Get issue details: Full details including description, status, sprint, transitions, comments, and attachments
Mutate issues: Create, update, transition, comment, link, add to sprints, and log work
Manage comments: Add, update, or delete comments
Manage versions: Create, update, release, archive, or delete fix versions
Get attachments: Inline decoding — images (resized), animated GIFs/video (sampled frames), audio (passthrough), PDFs (text extracted or rasterized), text/JSON; oversized files saved to disk
Bitbucket Tools
Search: Discover PRs (including your inbox), repositories, and branches
Get PR details: Full metadata, commits, comments, blockers, build status, optional diff, and referenced attachments
Mutate PRs: Create/update PRs; approve, unapprove, merge, or decline
Manage PR comments: Add, update, or delete comments; supports code suggestions
Get file contents: Raw file content from any branch, tag, or commit
Manage PR tasks: List, create, resolve, reopen, or delete checklist tasks
Get attachments: Same decoding pipeline as Jira attachments
Compatible with MCP clients such as Claude, Cursor, Windsurf, Zed, OpenCode, and Codex CLI, configured via a JSON file or environment variables.
Provides tools for self-hosted Atlassian products (Jira and Bitbucket), including workflow automation across tickets and pull requests.
Allows interaction with self-hosted Bitbucket instances for managing pull requests, repositories, branches, comments, tasks, and file content.
Allows interaction with self-hosted Jira instances for managing issues, projects, sprints, versions, comments, attachments, and work logs.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@atlassian-mcpshow my PRs waiting for review"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
atlassian-mcp
A Model Context Protocol (MCP) server for self-hosted Jira (Server / Data Center) and self-hosted Bitbucket (Server / Data Center). Exposes tools for natural-language workflows around tickets, pull requests, review threads, and git context.
Note: This server only supports self-hosted instances. Jira Cloud and Bitbucket Cloud use different APIs and are not supported.
Tools
Workflow
Tool | Description |
| Master entry point: git state + linked Jira ticket + open PR with reviewer/blocker status and next-step hints |
| Start a Jira ticket: fetches it, creates a local branch ( |
| Close out finished work: merges the open PR and transitions the Jira ticket to Done |
Git
Tool | Description |
| Branch, upstream state, remote URL, recent commits, working tree status, diff stat, and Jira keys in branch name |
| Diff of uncommitted changes or between two refs; supports paging via |
Jira
Tool | Description |
| Discover resources: |
| Full details for one issue: summary, description, status, sprint, transitions, comments, and attachment list |
| Fetch a Jira attachment by ID. Images, videos, animated images (GIF/APNG/animated WebP), audio, and PDFs are all decoded inline so the model can see/hear them. Text/JSON inline. Oversized or non-renderable attachments are auto-saved to a temp file and the path is returned. |
| Create, update, transition, comment, link, add to sprint, or log work — all in one call |
| Add, update, or delete a comment on an issue ( |
| Manage fix versions/releases ( |
Bitbucket
Tool | Description |
| Discover resources: |
| Full PR details: metadata, commits, comments, blockers, build status, optional diff, and any attachments referenced from the description or comments |
| Fetch a repo attachment by ID. Same decoding pipeline as |
| Create/update a PR, or perform lifecycle actions: |
| Add, update, or delete a PR comment; for code changes use |
| Raw file content from Bitbucket at a branch, tag, or commit |
| Manage PR tasks (checklist items): |
Natural language examples
"what am I working on?" →
get_dev_context"make a branch for FOO-123" →
start_work"ship this / merge and close the ticket" →
complete_work"show my PRs waiting for review" →
bitbucket_searchwithmine=true"list open PRs for this repo from feature/ABC-123" →
bitbucket_searchwithfromBranch"give me a full overview of PR 42" →
bitbucket_get_pr"open a PR from my current branch to master" →
bitbucket_mutatewithcreate"approve / merge / decline PR 42" →
bitbucket_mutatewithaction"reply to comment 123 on PR 42" →
bitbucket_commentwithcommentId=123"resolve this blocker on PR 42" →
bitbucket_commentwithaction=update,severity=BLOCKER,state=RESOLVED"list PR checklist tasks" →
bitbucket_pr_taskswithaction=list"find bugs assigned to me in PAY project" →
jira_searchwithmine=true,issueType=Bug"what's in the current sprint?" →
jira_searchwithresource=board_overview"move FOO-123 to In Progress" →
jira_mutatewithtransitionName="In Progress""log 2h on FOO-123" →
jira_mutatewithworklog"create version 9.1.0 in PAY" →
jira_versionwithaction=create,projectKey=PAY,name=9.1.0"list releases for PAY" →
jira_searchwithresource=versions,project=PAY"release version 12345" →
jira_versionwithaction=release,id=12345"set fix version 9.1.0 on FOO-123" →
jira_mutatewithupdate.fixVersion=9.1.0"create a task under epic FOO-100" →
jira_mutatewithcreate.issueType=Task,create.parent=FOO-100(auto-detects Epic and sets Epic Link)"move FOO-123 under epic FOO-100" →
jira_mutatewithupdate.epicLink=FOO-100
Related MCP server: Bitbucket Server MCP
Setup
1. Create a config file
Create ~/.atlassian-mcp.json:
{
"$schema": "https://raw.githubusercontent.com/stubbedev/atlassian-mcp/master/atlassian-mcp.schema.json",
"jira": {
"url": "https://jira.example.com",
"token": "your-jira-personal-access-token"
},
"bitbucket": {
"url": "https://bitbucket.example.com",
"token": "your-bitbucket-personal-access-token"
}
}The $schema field is optional but enables editor autocomplete and validation.
projectKeymeans a project code:Jira example:
PAYin ticketPAY-123Bitbucket example: project
ENGin repo pathENG/payments-service
You can also use ergonomic aliases:
Jira:
project(alias ofprojectKey)Bitbucket:
projectandrepo(aliases ofprojectKeyandrepoSlug)
For Bitbucket tools,
projectKeyandrepoSlugare usually auto-detected from your localoriginremote.bitbucket_create_pull_requestalso auto-detectsfromBranchfrom your current branch and returns the existing open PR if one already exists for that branch.Jira project-scoped calls accept
projectKeyand work best when provided.If
projectKeyis omitted for Jira issue creation/type lookup, the server tries to infer it from your current branch ticket key, falls back to auto-select when only one project is visible, and otherwise returns a numbered project list to pick from.
Alternatively, use environment variables (or a .env file in this directory):
JIRA_URL=https://jira.example.com
JIRA_ACCESS_TOKEN=your-jira-personal-access-token
BITBUCKET_URL=https://bitbucket.example.com
BITBUCKET_ACCESS_TOKEN=your-bitbucket-personal-access-tokenConfig is resolved in this order: --config <path> CLI arg → ATLASSIAN_MCP_CONFIG env var → ~/.atlassian-mcp.json → .atlassian-mcp.json in cwd → environment variables.
2. Connect to your AI tool
No cloning or building required — just point your tool at npx @stubbedev/atlassian-mcp@latest and it will install and run automatically.
Note:
--prefer-onlinecan break MCP startup in some clients. Keep the command simple and use the update steps below when you want to refresh.
Claude Code
claude mcp add atlassian -- npx -y @stubbedev/atlassian-mcp@latest --config ~/.atlassian-mcp.jsonCursor
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-only):
{
"mcpServers": {
"atlassian": {
"command": "npx",
"args": ["-y", "@stubbedev/atlassian-mcp@latest", "--config", "/Users/you/.atlassian-mcp.json"]
}
}
}Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"atlassian": {
"command": "npx",
"args": ["-y", "@stubbedev/atlassian-mcp@latest", "--config", "/Users/you/.atlassian-mcp.json"]
}
}
}Zed
Add to ~/.config/zed/settings.json:
{
"context_servers": {
"atlassian": {
"command": {
"path": "npx",
"args": ["-y", "@stubbedev/atlassian-mcp@latest", "--config", "/home/you/.atlassian-mcp.json"]
}
}
}
}OpenCode
Add to opencode.json in your project root (or ~/.config/opencode/opencode.json for global):
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"atlassian": {
"type": "local",
"command": ["npx", "-y", "@stubbedev/atlassian-mcp@latest", "--config", "/home/you/.atlassian-mcp.json"]
}
}
}Codex CLI
Add to ~/.codex/config.yaml:
mcpServers:
atlassian:
command: npx
args:
- -y
- @stubbedev/atlassian-mcp@latest
- --config
- /home/you/.atlassian-mcp.jsonAny other MCP-compatible tool
Most tools that support MCP accept the same JSON format. Use npx as the command with ["-y", "@stubbedev/atlassian-mcp@latest", "--config", "/path/to/config.json"] as the args.
Updating existing installs
If your MCP client is already configured and you want the newest package version:
npx clear-npx-cacheThen restart your MCP client.
Manual install (optional)
If you prefer to clone and run locally:
git clone git@github.com:stubbedev/atlassian-mcp.git
cd atlassian-mcp
npm installThen use node /path/to/atlassian-mcp/dist/index.js instead of the npx command in the configs above.
Attachment decoding pipeline
The attachment tools (jira_get_attachment, bitbucket_get_attachment) decode binary attachments into model-readable content before returning them:
Input | What gets returned | How |
Static images (PNG/JPEG/WebP/AVIF/SVG…) | Resized image content blocks |
|
Animated images (GIF/APNG/animated WebP) | N sampled frames as image content blocks |
|
Video (mp4/webm/mov/…) | N sampled frames as image content blocks |
|
Audio (mp3/wav/ogg/…) | MCP audio content block | passthrough |
PDFs | Extracted text — or rasterized pages if text is empty (scanned PDFs) |
|
Text-like (json/xml/yaml/…) | Text content block | passthrough |
Everything else (or oversized) | Auto-saved to a temp file; path is returned |
|
Auto-saved files are periodically pruned by TTL and total-size quota — see Environment overrides below.
Native dependencies
sharp— image decode/resize. Ships prebuilt binaries for glibc Linux (x64/arm64), macOS, Windows. Alpine / musl users may neednpm install --cpu=x64 --os=linux --libc=musl sharp.ffmpeg-static+ffprobe-static— video/audio decode. ~80 MB bundled binary per platform. Override with env vars (below) if you have system ffmpeg.@napi-rs/canvas+unpdf— PDF text extraction and page rasterization.
Environment overrides
Variable | Purpose | Default |
| Path to | bundled |
| Path to | bundled |
| Auto-saved attachments older than this are pruned. |
|
| Total-size quota for auto-saved attachments in |
|
Releases (Maintainers)
This package is published to npm as @stubbedev/atlassian-mcp.
Use semantic versioning for releases. Breaking tool-surface changes should bump the minor version while <1.0.0 (for example 0.0.x -> 0.1.0).
Automatic publish is configured in .github/workflows/publish.yml and runs when a new version tag is pushed.
Release flow:
# choose one: patch | minor | major
increment=patch
# bumps package.json + package-lock.json,
# creates a version commit, and creates a git tag (for example v0.1.17)
npm version "$increment"
# push commit and tag to GitHub
git push origin HEAD --follow-tagsGitHub Actions will publish the npm release from that pushed tag.
The workflow is configured for npm Trusted Publisher (OIDC), so no
NPM_TOKENsecret is required
Required npm setup (one-time):
In npm package settings, add this GitHub repo/workflow as a Trusted Publisher
Creating Personal Access Tokens
Jira Server / Data Center
Personal Access Tokens are supported from Jira 8.14 onwards.
Log in to your Jira instance.
Click your profile avatar in the top-right corner and select Profile.
In the left sidebar, click Personal Access Tokens.
Click Create token.
Give the token a name (e.g.
atlassian-mcp) and optionally set an expiry date.Click Create and copy the token — it will only be shown once.
Paste the token as the token value under jira in your config file.
If your Jira version is older than 8.14, you can use HTTP Basic Auth instead — but this server only supports Bearer token (PAT) authentication.
Bitbucket Server / Data Center
Personal Access Tokens are supported from Bitbucket Server 5.5 onwards.
Log in to your Bitbucket instance.
Click your profile avatar in the top-right corner and select Manage account.
In the left sidebar, under Security, click Personal access tokens.
Click Create a token.
Give the token a name (e.g.
atlassian-mcp).Set the permissions:
Projects: Read
Repositories: Read + Write (Write is needed to create pull requests and add comments)
Optionally set an expiry date.
Click Create and copy the token — it will only be shown once.
Paste the token as the token value under bitbucket in your config file.
Development
# Watch mode — recompiles on file changes
npm run dev
# Run the built server directly
node dist/index.js
# Test the tool list
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | node dist/index.js
# Quick release smoke check
npm run smokeTo use a specific config file:
node dist/index.js --config /path/to/config.jsonMaintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/stubbedev/atlassian-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server