install-atlassian-mcp
Skill2 starsChanged 14 days agoMITView on GitHub
Install and configure the Atlassian MCP server (Jira and Confluence) for Claude or GitHub Copilot agents. Supports uvx (recommended) and Docker methods. Use when setting up Atlassian MCP, Jira MCP, Confluence MCP, or asked to install atlassian mcp.
- Pipes a download into a shell
- Reads credentials
- Installs packages
In this repository18 other files it gives its agents.
- ado-open-prSkill
- ado-pr-code-reviewSkill
- ado-pr-resolve-commentsSkill
- ado-pr-teams-notifySkill
- agent-playtestSkill
- explain-diff-htmlSkill
- generate-pr-notesSkill
- git-commit-conventional-strictSkill
- install-azure-devops-mcpSkill
- install-playwright-mcpSkill
- install-sentry-mcpSkill
- prd-to-sdd-specSkill
- sdd-qa-to-ticketSkill
- setup-project-configSkill
- spec-recalibrateSkill
- sync-api-specSkill
- tech-plan-to-ticketSkill
- tech-plan-to-wikiSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
All optional — anything not passed is asked in Step 1.
- Very specific: line 59
If ~/.env.mcp-atlassian already exists, the script detects it and asks whether to reuse those credentials — no re-entry needed
- Distinctive: line 63
Create API tokens at: https://id.atlassian.com/manage-profile/security/api-tokens
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Install Atlassian MCP
Install this skill
npx skills add jamesyang124/agent-skills --skill install-atlassian-mcp -gAdds Jira and Confluence access to your agent: create/search issues, read/write pages, manage sprints. Repository: https://github.com/sooperset/mcp-atlassian
Arguments
All optional — anything not passed is asked in Step 1.
| Token | Meaning |
claude / copilot | which agent to configure |
uvx / docker | install method (uvx recommended, no Docker required) |
The API token is never taken as an argument — it is collected in the terminal (Step 2).
Quick Start
Collect parameters, then run the bundled script. API tokens must be collected via terminal — never via a questions tool.
Step 1 — Collect parameters
Use vscode_askQuestions with:
- agent — which agent to configure
- options:
claude,copilot
- options:
- method — installation method
- options:
uvx(recommended, no Docker required),docker
- options:
- jira-url — Jira instance URL (e.g.
https://myteam.atlassian.net)
Step 2 — Run the installer
PROJECT_ROOT="<workspace-root>" \
bash "<skill-dir>/scripts/install.sh" \
--agent <agent> \
--method <method> \
--jira-url <jira-url><skill-dir> is this skill's folder, the base directory shown when the skill loads (for example ~/.claude/skills/install-atlassian-mcp).
- If
~/.env.mcp-atlassianalready exists, the script detects it and asks whether to reuse those credentials — no re-entry needed - API tokens are always prompted interactively in the terminal (hidden input) when no existing file is found
- Writes
~/.env.mcp-atlassianto your home directory (global, not per-project) and merges into the agent config
Create API tokens at: https://id.atlassian.com/manage-profile/security/api-tokens
Step 3 — Confirm
Tell the user: Restart your agent to load Atlassian MCP.
Prerequisites
uvx (recommended):
curl -LsSf https://astral.sh/uv/install.sh | shDocker (alternative): Docker must be installed and running (docker info).
What Gets Written
Copilot (.vscode/mcp.json) — uvx method:
{
"servers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "...",
"JIRA_USERNAME": "...",
"JIRA_API_TOKEN": "..."
}
}
}
}Claude (.mcp.json) use mcpServers key instead of servers.
The Docker config uses --env-file ~/.env.mcp-atlassian (global credential store).
Troubleshooting
uvx not found→ run the install command above, then restart your shelljq not found→brew install jqon macOS- Docker not running → start Docker Desktop and retry with
--method docker - Authentication errors → verify API token at https://id.atlassian.com/manage-profile/security/api-tokens
- Config not loading → confirm the agent was fully restarted after install
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

