Existing Atlassian MCP servers (Rovo, sooperset) require Docker, .env files, and mcp-remote bridges. They dump 72 tools into agent context and have known quirks that silently fail. a2atlassian fixes…
A2atlassian is an MCP project maintained in the agentic-eng/a2atlassian repository. The maintainer describes its purpose as “Existing Atlassian MCP servers (Rovo, sooperset) require Docker, .env files, and mcp-remote bridges. They dump 72 tools into agent context and have known quirks that…”. Read the project documentation for the complete scope.
The documented pypi package is a2atlassian. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares ATLASSIAN_TOKEN. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| login | Save a connection — validates by calling /myself first |
| logout | Remove a saved connection |
| list_connections | List connections (no secrets exposed) |
| jira_get_issue | Get issue by key — full fields, status, assignee |
| jira_search | Search by JQL with pagination — compact TSV output by default |
| jira_search_count | Count-only JQL — cheap pre-check for "is this going to be huge?" |
| jira_search_fields | Discover custom-field IDs by name |
| jira_get_field_options | List allowed values for a select / multi-select field |
| jira_get_comments | Get all comments for an issue |
| jira_get_worklogs | Get all worklogs for an issue |
| jira_get_transitions | Discover available status transitions |
| jira_get_link_types | List available issue-link types |
| jira_get_watchers | List watchers for an issue |
| jira_get_projects | List projects accessible to the connection |
| jira_get_project_metadata | Fetch creation metadata (issue types, required fields) |
| jira_get_user_profile | Resolve an email/accountId to a full user profile |
| jira_get_boards | List agile boards in a project |
| jira_get_board_issues | Issues on a board (paginated) |
| jira_get_sprints | List sprints on a board |
| jira_get_sprint_issues | Issues in a sprint (paginated) |
| jira_create_issue | Create a new issue |
| jira_update_issue | Update fields on an existing issue |
| jira_delete_issue | Delete an issue |
| jira_transition_issue | Move issue to a new status |
| jira_add_comment | Add comment (wiki markup, API v2) |
| jira_edit_comment | Update existing comment |
| jira_add_worklog | Log time on an issue |
| jira_create_issue_link | Link two issues |
| jira_remove_issue_link | Remove an issue link |
| jira_set_watchers | Replace the watcher set on an issue |
| jira_create_sprint | Create a sprint on a board |
| jira_update_sprint | Update sprint state / dates |
| jira_add_issues_to_sprint | Move issues into a sprint |
| jira_create_version | Create a project version |
| confluence_get_page | Fetch a page by id (body storage, version, space) |
| confluence_get_page_children | List direct children of a page (paginated) |
| confluence_search | CQL search; minimal per-match rows |
| confluence_upsert_pages | Batch create-or-update with preserve-on-omit body semantics + per-page status + partial-failure shape |
| confluence_set_page_properties | Metadata-only write (page_width, emoji, labels) — physically cannot touch body or title |
{
"mcpServers": {
"a2atlassian": {
"command": "uvx",
"args": [
"--from",
"a2atlassian",
"a2atlassian-mcp",
"--register",
"myproject",
"https://mysite.atlassian.net",
"user@company.com",
"${ATLASSIAN_TOKEN}"
],
"env": {
"ATLASSIAN_TOKEN": "YOUR_ATLASSIAN_TOKEN"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| ATLASSIAN_TOKEN | Declared in the maintainer’s client configuration. | Check documentation |
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
Connect the Notion MCP server to search workspace content and work with pages and databases through Notion’s hosted OAuth service.
Normalize a calendar handoff
A Model Context Protocol (MCP) server for Google Calendar integration in Claude Desktop with auto authentication support. This server enables AI assistants to manage Google Calendar through natural language interactions.
BugHerd bug tracking integration. List projects, tasks, comments with filtering.
Extrai restaurantes do iFood no Brasil com endereço, categoria e CNPJ da Receita Federal.