a2atlassian
Provides AI agents with access to Atlassian Cloud services (Jira and Confluence) through pre-configured connections with scoped access controls, read-only defaults, and support for multiple projects.
Planned support for managing Confluence pages, comments, attachments, labels, and search functionality (Phase 3 roadmap).
Enables issue management via JQL search, status transitions, and comment operations (add/edit) with compact TSV output for lists and error enrichment for invalid fields or JQL syntax.
Agent: "What's the status of PROJ-42? Add a comment with the progress update."
↓
a2atlassian → get issue, add comment, transition to In Progress
↓
Agent: "Done — PROJ-42 updated and moved to In Progress."Why a2atlassian?
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 all of that:
No Docker —
pip install a2atlassianand you're donePre-configured connections — define projects in
.mcp.jsonwith--register, agent works immediatelyRead-only by default — write access is opt-in per connection
Connection scoping —
--scopelimits which projects an agent can seeCompact output — TSV for lists (30-60% fewer tokens), JSON for single entities
Dynamic tool loading — MCP clients that support deferred tools (e.g., Claude Code) load tools on demand, keeping context lean
Error enrichment — bad field names get suggestions, JQL typos get corrections, quirks get auto-fixed
Secrets stay in env —
${ATLASSIAN_TOKEN}in configs, expanded only at runtime
Quick Start
# Recommended — installs globally as a CLI tool
uv tool install a2atlassian
# Or with pip
pip install a2atlassianAs an MCP Server (recommended)
Claude Code (with pre-configured connection):
claude mcp add -s user a2atlassian -- uvx --from a2atlassian a2atlassian-mcp \
--register myproject https://mysite.atlassian.net user@company.com '${ATLASSIAN_TOKEN}'Claude Code (minimal — agent calls login on demand):
claude mcp add -s user a2atlassian -- uvx --from a2atlassian a2atlassian-mcpClaude Desktop / Cursor / any MCP client (.mcp.json):
{
"mcpServers": {
"a2atlassian": {
"command": "uvx",
"args": [
"--from", "a2atlassian", "a2atlassian-mcp",
"--register", "myproject", "https://mysite.atlassian.net",
"user@company.com", "${ATLASSIAN_TOKEN}"
],
"env": {
"ATLASSIAN_TOKEN": "your-api-token-here"
}
}
}
}Multiple projects:
{
"args": [
"--from", "a2atlassian", "a2atlassian-mcp",
"--register", "myproject", "https://mysite.atlassian.net", "user@a.com", "${TOKEN_A}",
"--register", "personal", "https://personal.atlassian.net", "user@b.com", "${TOKEN_B}"
]
}Scoped connections (limit agent to specific saved projects):
{
"args": ["--from", "a2atlassian", "a2atlassian-mcp", "--scope", "myproject"]
}--register creates ephemeral in-memory connections (process lifetime, no files written). --scope filters which saved connections are visible. Both limit blast radius.
As a CLI
# Save a connection (validates by calling /myself)
a2atlassian login -p myproject \
--url https://mysite.atlassian.net \
--email user@company.com \
--token "$ATLASSIAN_TOKEN"
# Enable writes
a2atlassian login -p myproject \
--url https://mysite.atlassian.net \
--email user@company.com \
--token "$ATLASSIAN_TOKEN" \
--no-read-only
# List / remove connections
a2atlassian connections
a2atlassian logout -p myprojectMCP Tools
Connection Management
Tool | Description |
| Save a connection — validates by calling /myself first |
| Remove a saved connection |
| List connections (no secrets exposed) |
Jira — Read
Tool | Description |
| Get issue by key — full fields, status, assignee |
| Search by JQL with pagination — compact TSV output by default |
| Get all comments for an issue |
| Discover available status transitions |
Jira — Write (requires read-write connection)
Tool | Description |
| Add comment (wiki markup, API v2) |
| Update existing comment |
| Move issue to new status |
Output Formats
All tools accept a format parameter:
Format | Default for | Description |
| Lists (search, comments) | TSV with header — shape once, data many. 30-60% fewer tokens than JSON |
| Single entities (get_issue) | Standard JSON with metadata envelope |
List responses use a compact TSV-style format (header row + tab-separated values) inspired by TOON. This is the same approach a2db uses — column names appear once, then just values. For a 50-issue search result, this typically saves 40-60% of tokens compared to JSON.
TSV example (search results):
# search (23 results, 50ms, truncated: False)
key summary assignee status
PROJ-142 Fix auth timeout Alice Smith In Progress
PROJ-141 Add search filters Bob Jones To DoJSON example (single issue):
{
"data": {"key": "PROJ-142", "fields": {"summary": "Fix auth timeout", ...}},
"count": 1,
"truncated": false,
"time_ms": 85
}Error Enrichment
When something fails, a2atlassian tells the agent what to do:
Field 'asignee' does not exist
Did you mean: assignee?Connection 'myproject' is read-only.
Run: a2atlassian login -p myproject --read-only falseQuirks handled automatically:
Assignee requires display name (not
712020:account IDs) — auto-detected with hintParent field must be plain string —
{"key": "PROJ-14"}normalized to"PROJ-14"silentlyIssue type conversion not supported via API — clear Jira UI instructions provided
Security
Read-Only by Default
Every connection starts read-only. Write tools check the connection flag before executing:
Connection 'myproject' is read-only.
Re-run 'a2atlassian login -p myproject --read-only false' to enable writes.The human operator controls write access — not the agent.
Credential Storage
Connections saved via login go to ~/.config/a2atlassian/connections/ as TOML files:
File permissions:
0600(owner read/write only)${ATLASSIAN_TOKEN}syntax — env var references stored literally, expanded at runtimeNo secrets in output —
list_connectionsshows project name, URL, and mode — never tokensEphemeral mode —
--registerkeeps credentials in memory only, never written to disk
Connection Scoping
Use --scope to limit which saved connections a specific MCP instance can access:
# Project config — only myproject visible, even if other connections are saved
uvx --from a2atlassian a2atlassian-mcp --scope myprojectProject-level MCP configs (.claude/mcp.json) override global configs — each repo sees only its own connections.
Rate Limiting
Built-in retry with exponential backoff for Atlassian's rate limits (429) and transient server errors (500). Two retries at 1s and 3s intervals before surfacing the error.
Comparison
Feature | a2atlassian | Rovo (official) | sooperset/mcp-atlassian |
Setup |
| OAuth + Docker | Docker + .env + mcp-remote |
Tools in context | 10 (Phase 1) | ~72 | ~72 |
Connection management | TOML + | Per-session OAuth | .env file |
Multi-project | Yes (scoped) | No | One .env per setup |
Read-only default | Yes (per-connection) | No | No |
Output format | TSV + JSON | JSON | JSON |
Error enrichment | Field suggestions, quirk fixes | Generic errors | Generic errors |
Quirk handling | Auto-fix (assignee, parent) | Documented workarounds | Documented workarounds |
Rate limiting | Built-in retry | No | No |
CLI | Yes | No | No |
License | Apache 2.0 | Proprietary | MIT |
Roadmap
Phase 1 (current): Jira core — get/search issues, comments (CRUD), transitions. The secondary critical path.
Phase 2: Full Jira surface — sprints, boards, links, projects, fields, worklogs, attachments, watchers.
Phase 3: Confluence — pages, comments, attachments, labels, search.
Setup by Environment
Local (macOS / Linux)
# Recommended
uv tool install a2atlassian
# Or with pip
pip install a2atlassian
# CLI
a2atlassian login -p myproject --url https://mysite.atlassian.net --email me@co.com --token "$TOKEN"
# Or add as MCP server (see Quick Start)CI / Automation
uv tool install a2atlassian
# Pre-configured — no login needed
uvx --from a2atlassian a2atlassian-mcp --register ci https://mysite.atlassian.net ci-user@co.com "${CI_ATLASSIAN_TOKEN}"Development
make bootstrap # Install deps + hooks
make check # Lint + test + security (full gate)
make test # Tests with coverage
make lint # Lint only (never modifies files)
make fix # Auto-fix + lintLicense
Apache 2.0
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/agentic-eng/a2atlassian'
If you have feedback or need assistance with the MCP directory API, please join our Discord server