atlassian-mcp

An agent skill by Jeffallan, from Jeffallan/claude-skills. Tags: api, automation, developer-tools, documentation, mcp, slack.

What it does

Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use when querying Jira issues with JQL filters, creating and updating tickets with custom fields, searching or editing Confluence pages with CQL, managing sprints and backlogs, setting up MCP server authentication, syncing documentation, or debugging Atlassian API integrations.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add Jeffallan/claude-skills --skill atlassian-mcp

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/Jeffallan/claude-skills
cp -r claude-skills/skills/atlassian-mcp ~/.claude/skills/atlassian-mcp

Safety box score

Grade D, elevated risk: 54 of 100 risk points, rated 2026-09-29. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill configures and drives an Atlassian MCP integration that can read and write Jira and Confluence data, including bulk workflow automation like issue triage, sprint operations, and release-note publishing. The main risks are executing third-party package code, exposing Atlassian credentials, and making broad networked changes to project data and documentation.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	3 (high)	It explicitly installs and runs external packages via commands like `npx @anthropic/mcp-atlassian`, `uv tool install mcp-atlassian`, `pip install mcp-atlassian`, and `npm install atlassian-mcp`, which can execute downloaded code from registries.
Network access	2 (moderate)	The skill is built around authenticated calls to Atlassian and auth endpoints, e.g. `fetch('https://auth.atlassian.com/oauth/token'...)`, `curl -I https://your-company.atlassian.net`, and `curl -u ... /rest/api/3/myself`.
Filesystem reach	2 (moderate)	Setup writes into the user's home configuration, including `~/Library/Application Support/Claude/claude_desktop_config.json` and `~/.config/claude/claude_desktop_config.json`, which is outside the project tree.
Secrets & credentials	2 (moderate)	It requires handling API tokens, PATs, and OAuth secrets such as `JIRA_API_TOKEN`, `CONFLUENCE_API_TOKEN`, `JIRA_PERSONAL_TOKEN`, `client_secret`, and `ATLASSIAN_CLIENT_SECRET`.
Privilege & persistence	1 (low)	It includes user-global install steps like `npm install -g @anthropic/mcp-atlassian`, but nothing here requires sudo or system service registration.
Instruction hijack surface	0 (none)	The files do not tell the agent to ignore instructions, skip confirmations, or follow hidden/remote prompts; instead they explicitly say to confirm before write or bulk operations.
Irreversible actions	2 (moderate)	It can create, update, comment on, and transition Jira issues, create/update Confluence pages, move issues into sprints, and sync meeting notes into tickets; those are inherently write-capable workflows even though the skill asks for confirmation first.
Transparency	2 (moderate)	The repo ships only markdown docs; the actual runtime behavior comes from external packages referenced by name (`@anthropic/mcp-atlassian`, `mcp-atlassian`, `atlassian-mcp`) rather than code in the repo.

Before installing

Review `references/mcp-server-setup.md` and decide whether to trust the registry-fetched server packages or pin a reviewed version first.
Use a throwaway Atlassian account or read-only project and verify only `jira_get_issue` / `confluence_search` before enabling any write tools.
Check the Claude Desktop config path for your OS (`.../claude_desktop_config.json`) before and after install to ensure nothing unexpected was added.
Keep `JIRA_API_TOKEN`, `CONFLUENCE_API_TOKEN`, and any OAuth client secrets out of `.env` files and out of logged output.

Rated 2026-09-29 by an automated review of 6 files from the skill's repository.

Source

Repository: Jeffallan/claude-skills (all skills from this repository)
Path: skills/atlassian-mcp/SKILL.md
Branch: main
Updated: 2026-09-19

legacy-modernizer — Designs incremental migration strategies, identifies service boundaries, produces dependency maps and migration roadmaps.
mcp-developer — Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources.
hyperframes-registry — Search, install, and wire registry blocks and components into HyperFrames compositions.
agents-connect — Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies.
cli-developer — Use when building CLI tools, implementing argument parsing, or adding interactive prompts.
code-documenter — Generates, formats, and validates technical documentation — including docstrings, OpenAPI/Swagger specs, JSDoc annotations, doc portals, and user guides.