atlassian-ai-toolkit-mcp
MCP server for AI assistants to interact with Atlassian Jira and Confluence Cloud APIs through typed tools and secure authentication.
README
Atlassian AI Toolkit
AI-first SDK, CLI, and MCP server for Atlassian Jira and Confluence
A Bun monorepo containing a typed SDK, an agent-native CLI, and an MCP server for Atlassian Cloud APIs.
Packages
| Package | Description |
|---|---|
@atlassian-ai-toolkit/sdk |
Core SDK with types, API client, and business logic |
@atlassian-ai-toolkit/cli |
Command-line interface (Stricli) |
@atlassian-ai-toolkit/mcp |
MCP server for AI assistants (FastMCP) |
Install The CLI
Recommended: Standalone Binary
No Node.js, no npm, no PATH conflicts. One file built with Bun.
macOS and Linux:
curl -fsSL https://raw.githubusercontent.com/spenserhale/atlassian-ai-toolkit/main/scripts/install.sh | sh
The script detects your OS + architecture, downloads the matching binary from the latest release, verifies its SHA256, and installs to $HOME/.local/bin/atlassian-ai.
Pin a version with ATLASSIAN_AI_TOOLKIT_VERSION=v0.1.0 or change the install directory with ATLASSIAN_AI_TOOLKIT_INSTALL=$HOME/bin.
Windows: download atlassian-ai-windows-x64.exe from the latest release and put it on your PATH.
Available binaries: atlassian-ai-linux-{x64,arm64}, atlassian-ai-darwin-{x64,arm64}, and atlassian-ai-windows-x64.exe.
Configure
Set Atlassian Cloud credentials in your shell:
export ATLASSIAN_SITE_URL="https://your-site.atlassian.net"
export ATLASSIAN_EMAIL="you@example.com"
export ATLASSIAN_API_TOKEN="your-api-token"
Create a scoped API token at https://id.atlassian.com/manage-profile/security/api-tokens.
Destructive Actions
Deletes preview by default. Actual deletion requires --force and a matching --confirm value from the fetched resource.
# Preview the permanent Jira delete
atlassian-ai jira delete PROJ-123
# Permanently delete the Jira issue
atlassian-ai jira delete PROJ-123 --force --confirm PROJ-123
# Preview moving a Confluence page to trash
atlassian-ai confluence delete 123456
# Move a Confluence page to trash
atlassian-ai confluence delete 123456 --force --confirm 123456
# Permanently purge an already-trashed Confluence page
atlassian-ai confluence delete 123456 --purge --force --confirm 123456
Getting Started From Source
# Install dependencies
bun install
# Build all packages
bun run build
# Run the CLI
bun run dev:cli -- --help
# Run the MCP server (stdio mode for Claude Desktop)
bun run dev:mcp
The token should be scoped to the smallest set of Jira and Confluence permissions needed for the workflow. Third-party reference implementations live under refs/, which is intentionally gitignored so this repo never vendors or executes unreviewed code with local credentials.
Architecture
packages/sdk/ <-- Types, API client, business logic (foundation)
^ ^
| |
packages/cli/ packages/mcp/
(Stricli) (FastMCP)
Both the CLI and MCP server are thin wrappers over the SDK. If the REST API changes, you update the SDK and both consumers get the fix automatically.
Development
# Run tests across all packages
bun test
# Build a specific package
cd packages/sdk && bun run build
Adding a New API Operation
- Add types to
packages/sdk/src/types.ts - Add the client method to
packages/sdk/src/client.ts - Add a CLI command in
packages/cli/src/commands/ - Add an MCP tool in
packages/mcp/src/tools/
Destructive operations must default to a preview path and require an explicit --force flag in the CLI or force: true in MCP tools.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.