a2atlassian allows AI agents to access Jira and Confluence with pre-configured connections and read-only access by default.
From the registry: Jira & Confluence for AI agents. Pre-configured connections, compact output.
$ curl -LsSf https://astral.sh/uv/install.sh | shhttps://docs.astral.sh/uv/Please install the `a2atlassian` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10+ and uv** — uvx is used to run a2atlassian-mcp. Install uv (which provides uvx) via the official installer. Run: `curl -LsSf https://astral.sh/uv/install.sh | sh` (https://docs.astral.sh/uv/)
- **Create an Atlassian API token** — Generate an API token for your Atlassian account to authenticate against Jira/Confluence. (https://id.atlassian.com/manage-profile/security/api-tokens)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","a2atlassian","a2atlassian-mcp"]
- required environment variables:
- `ATLASSIAN_TOKEN`: Atlassian API token referenced as ${ATLASSIAN_TOKEN} inside --register args. (example: `<your-atlassian-api-token>`)
Note: Read-only by default. Use --register <name> <url> <email> '${ATLASSIAN_TOKEN}' to pre-configure a connection, or call the `login` tool at runtime.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.ATLASSIAN_TOKENrequiredAPI token for authenticating with Atlassian servicesAtlassian Rovo MCP Server