mcp-atlassian is a Model Context Protocol server that lets AI assistants work with Atlassian's Confluence and Jira services. Developers use it to search documentation, find issues, create tickets, and update Jira work through an assistant, with support for Cloud and Server/Data Center deployments. The catalogue entries provide instructions and settings for using the server.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/sooperset/mcp-atlassian/copilot-instructionsgit clone --depth 1 https://github.com/sooperset/mcp-atlassianWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/sooperset/mcp-atlassian/copilot-instructions)<a href="https://agentmods.dev/instructions/sooperset/mcp-atlassian/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sooperset/mcp-atlassian/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01180 | $0.01180 |
| Opus 5 | $0.00590 | $0.00590 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
mcp-atlassian copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
8 near-identical copies found in the catalogue:
- atlassian-mcp copilot-instructions.md — 100% identical, 0 lines differ
- ai_agent_mcp_jira copilot-instructions.md — 100% identical, 0 lines differ
- AtlMCPforDC copilot-instructions.md — 100% identical, 0 lines differ
- mcp-atlassian-with-bitbucket copilot-instructions.md — 100% identical, 0 lines differ
- atlassian-mcp-server copilot-instructions.md — 100% identical, 0 lines differ
- mcp-atlassian copilot-instructions.md — 100% identical, 0 lines differ
- jira-mcp copilot-instructions.md — 100% identical, 0 lines differ
- mcp-atlassian-dc copilot-instructions.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Atlassian - Development Guide
Model Context Protocol (MCP) server for Atlassian products (Jira & Confluence). Python ≥3.10.
Build, Test, and Lint
Dependencies:
uv sync --frozen --all-extras --dev # Install all dependencies
Code Quality (required before commit):
pre-commit run --all-files # Run all checks: ruff, prettier, mypy
Testing:
# Run all tests
uv run pytest
# Run with coverage
uv run pytest --cov=mcp_atlassian
# Run single test file
uv run pytest tests/unit/test_preprocessing.py
# Run single test function
uv run pytest tests/unit/test_preprocessing.py::test_specific_function
Running the Server:
uv run mcp-atlassian # Start MCP server
uv run mcp-atlassian --oauth-setup # OAuth configuration wizard
uv run mcp-atlassian -v # Verbose logging mode
Architecture
Mixin-Based Composition
Functionality is organized into focused mixins that compose together:
- Jira:
JiraFetcherinherits from 13 feature mixins (ProjectsMixin, IssuesMixin, WorklogMixin, etc.) - Confluence:
ConfluenceFetcherinherits from 7 feature mixins (SearchMixin, PagesMixin, SpacesMixin, etc.)
Each mixin lives in its own module under src/mcp_atlassian/jira/ or src/mcp_atlassian/confluence/.
Client + Fetcher Pattern
- Client classes (
JiraClient,ConfluenceClient): Authentication, configuration, and API session management - Fetcher classes (
JiraFetcher,ConfluenceFetcher): Business operations by composing mixins; inherit from Client
Protocol-Based Dependencies
Mixins declare dependencies via Protocol interfaces instead of direct imports:
class IssuesMixin(AttachmentsOperationsProto, FieldsOperationsProto):
# Mixin knows it needs attachment and field operations
# Protocols define the contract without circular imports
The final Fetcher class satisfies all protocols through multiple inheritance.
Data Models
- All models extend
ApiModelbase class withfrom_api_response()for deserialization - Use
TimestampMixinfor timestamp handling across Jira/Confluence models - Models support
to_simplified_dict()for MCP tool responses - Located in
src/mcp_atlassian/models/
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 136 lines · 1,180 tokens per session scan A 45a5eaee76b1
mcp-atlassian copilot-instructions.md is an instructions file published in the GitHub repository sooperset/mcp-atlassian (5,853 stars, last pushed today), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
atlassian-skills CLAUDE.md
Instructions for eunsanMountain/atlassian-skills, covering atlassian-skills — claude.md, project overview, build & run, install (uv recommended) and run the cli.
mcp-atlassian-extended AGENTS.md
Instructions for vish288/mcp-atlassian-extended, covering mcp-atlassian-extended — agent context, architecture, patterns, mcp compliance rules and tool annotations (mandatory).
mcp-atlassian-extended GEMINI.md
Instructions for vish288/mcp-atlassian-extended, covering mcp-atlassian-extended — gemini cli extension context, tool categories, jira, confluence and common workflows.
atlassian-server-mcp AGENTS.md
AGENTS.md instructions for zaimokuza-yoshiteru/atlassian-server-mcp, covering agent conventions, generated files, e2e operation-level reconciliation, run evidence chain and release evidence chain.
ConfluenceMcp CLAUDE.md
Claude Code instructions for jagadeesh52423/ConfluenceMcp, covering claude.md, development commands, building and running, build the typescript project and start the mcp server (production).
atlassian-skills AGENTS.md
Instructions for eunsanMountain/atlassian-skills, a project described as: Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact output, lossless XHTML Markdown round-trip, Claude Code + Codex + GitHub Copilot integration.