Skip to main content
Glama
spenserhale

atlassian-ai-toolkit-mcp

by spenserhale

Atlassian AI Toolkit

面向 Atlassian Jira 和 Confluence 的 AI 优先 SDK、CLI 和 MCP 服务器

一个包含类型化 SDK、面向代理的 CLI 以及 Atlassian Cloud API 的 MCP 服务器的 Bun 单体仓库。

描述

@atlassian-ai-toolkit/sdk

包含类型、API 客户端和业务逻辑的核心 SDK

@atlassian-ai-toolkit/cli

命令行界面(Stricli)

@atlassian-ai-toolkit/mcp

面向 AI 助手的 MCP 服务器(FastMCP)

Related MCP server: MCP Atlassian

安装 CLI

推荐:独立二进制文件

无需 Node.js、无需 npm、无 PATH 冲突。一个由 Bun 构建的文件。

macOS 和 Linux:

curl -fsSL https://raw.githubusercontent.com/spenserhale/atlassian-ai-toolkit/main/scripts/install.sh | sh

该脚本会检测你的操作系统和架构,从最新版本下载匹配的二进制文件,验证其 SHA256,并安装到 $HOME/.local/bin/atlassian

使用 ATLASSIAN_AI_TOOLKIT_VERSION=v0.1.0 固定版本,或使用 ATLASSIAN_AI_TOOLKIT_INSTALL=$HOME/bin 更改安装目录。

Windows:最新版本下载 atlassian-windows-x64.exe 并将其放入你的 PATH

可用二进制文件:atlassian-linux-{x64,arm64}atlassian-darwin-{x64,arm64}atlassian-windows-x64.exe

升级

从最新的 GitHub 版本就地升级已安装的二进制文件(首先验证 SHA256):

atlassian upgrade            # apply the latest release
atlassian upgrade --dry-run  # only show current vs latest

在 Windows 上,升级前请关闭正在运行的实例,或从最新版本重新下载 exe。

Shell 别名

为了使用更短的命令,请在 shell 配置文件中添加以下别名(~/.zshrc~/.bashrc):

alias jira='atlassian jira'
alias conf='atlassian confluence'

然后 jira get PROJ-123 会运行 atlassian jira get PROJ-123conf get 123456 会运行 atlassian confluence get 123456

配置

在 shell 中设置 Atlassian Cloud 凭据:

export ATLASSIAN_SITE_URL="https://your-site.atlassian.net"
export ATLASSIAN_EMAIL="you@example.com"
export ATLASSIAN_API_TOKEN="your-api-token"

https://id.atlassian.com/manage-profile/security/api-tokens 创建作用域 API 令牌。

附件

向 Jira 问题上传一个或多个文件。重复使用 --file 可上传多个文件;存储的文件名是文件的基名,MIME 类型根据文件扩展名推断。

# Attach a single file
atlassian jira attach PROJ-123 --file ./screenshot.png

# Attach several files and print the API response
atlassian jira attach PROJ-123 --file ./error.log --file ./har-capture.har --json

MCP 工具 jira_add_attachment 接受相同的 paths,外加一个 files 数组,用于代理内联生成的内容(filenamecontentencoding: utf8 | base64)。

Confluence 页面每次调用只接受一个附件:

atlassian confluence attachment upload --page 123456 --file ./diagram.png

必须在站点上启用附件功能,并且上传受站点最大附件大小的限制。

破坏性操作

默认情况下删除为预览模式。实际删除需要 --force 和匹配的 --confirm 值,该值来自获取的资源。

# Preview the permanent Jira delete
atlassian jira delete PROJ-123

# Permanently delete the Jira issue
atlassian jira delete PROJ-123 --force --confirm PROJ-123

# Preview moving a Confluence page to trash
atlassian confluence delete 123456

# Move a Confluence page to trash
atlassian confluence delete 123456 --force --confirm 123456

# Permanently purge an already-trashed Confluence page
atlassian confluence delete 123456 --purge --force --confirm 123456

从源码开始

# 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

令牌的作用域应设置为工作流所需的最小 Jira 和 Confluence 权限集。第三方参考实现位于 refs/ 下,该目录有意被 gitignore,因此此仓库永远不会使用本地凭据打包或执行未经审查的代码。

架构

packages/sdk/     <-- Types, API client, business logic (foundation)
    ^       ^
    |       |
packages/cli/   packages/mcp/
    (Stricli)    (FastMCP)

CLI 和 MCP 服务器都是 SDK 之上的轻量封装。如果 REST API 发生变化,你只需更新 SDK,两个使用者都会自动获得修复。

开发

# Run tests across all packages
bun test

# Build a specific package
cd packages/sdk && bun run build

添加新的 API 操作

  1. packages/sdk/src/types.ts 中添加类型

  2. packages/sdk/src/client.ts 中添加客户端方法

  3. packages/cli/src/commands/ 中添加 CLI 命令

  4. packages/mcp/src/tools/ 中添加 MCP 工具

破坏性操作必须默认为预览路径,并在 CLI 中要求显式的 --force 标志,或在 MCP 工具中要求 force: true

F
license - not found
Not graded
quality - not tested
A
maintenance

Maintenance

Maintainers
Response time
1wRelease cycle
8Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that enables AI assistants to interact with Atlassian Jira and Confluence across Cloud and Server/Data Center environments. It supports tasks like searching and summarizing documentation, managing Jira issues, and creating content through natural language.
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    MCP server that provides AI assistants with access to Jira Cloud for issue management, search, and workflow operations.

View all related MCP servers

Related MCP Connectors

  • MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.

  • MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.

  • MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.

View all MCP Connectors

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/spenserhale/atlassian-ai-toolkit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server