mcp-atlassian
MCP Atlassian
用于 Atlassian 产品(Confluence 和 Jira)的模型上下文协议(MCP)服务器。支持云和服务器/数据中心部署。
渐进式分支配置
此分支保留上游直接的 Atlassian MCP 表面,并添加由 MCP_PROFILE=progressive 控制的本地渐进式配置。在渐进式模式下,服务器仅暴露发现/模式/执行包装器,如 jira_discover、jira_capability_schema、jira_execute_read 和 jira_execute_write_guarded,而不是完整的直接工具表面。
上游 sooperset/mcp-atlassian 目前不包含此渐进式层,因此必须选择性地协调上游更新。不要盲目合并上游,否则渐进式包/测试可能会被移除。参见 FORK_WORKFLOW.md。
https://github.com/user-attachments/assets/35303504-14c6-4ae4-913b-7c25ea511c3e
https://github.com/user-attachments/assets/7fe9c488-ad0c-4876-9b54-120b666bb785
Related MCP server: MCP Atlassian
快速开始
1. 获取你的 API 令牌
前往 https://id.atlassian.com/manage-profile/security/api-tokens 并创建一个令牌。
对于服务器/数据中心,请改用个人访问令牌。参见 身份验证。
2. 配置你的 IDE
添加到你的 Claude Desktop 或 Cursor MCP 配置中:
{
"mcpServers": {
"mcp-atlassian": {
"command": "uvx",
"args": ["mcp-atlassian"],
"env": {
"JIRA_URL": "https://your-company.atlassian.net",
"JIRA_USERNAME": "your.email@company.com",
"JIRA_API_TOKEN": "your_api_token",
"CONFLUENCE_URL": "https://your-company.atlassian.net/wiki",
"CONFLUENCE_USERNAME": "your.email@company.com",
"CONFLUENCE_API_TOKEN": "your_api_token"
}
}
}
}服务器/数据中心用户:使用
JIRA_PERSONAL_TOKEN而不是JIRA_USERNAME+JIRA_API_TOKEN。详情参见 身份验证。
Autohand Code
使用相同的 uvx 服务器和你的 Atlassian 凭据:
autohand mcp add mcp-atlassian env \
JIRA_URL=https://your-company.atlassian.net \
JIRA_USERNAME=your.email@company.com \
JIRA_API_TOKEN=your_api_token \
CONFLUENCE_URL=https://your-company.atlassian.net/wiki \
CONFLUENCE_USERNAME=your.email@company.com \
CONFLUENCE_API_TOKEN=your_api_token \
uvx mcp-atlassian在 add 后添加 --scope project 以将配置保留在当前项目中。有关当前安装和 CLI 详细信息,请参见 Autohand Code。
3. 开始使用
让你的 AI 助手:
"查找 PROJ 项目中分配给我的问题"
"在 Confluence 中搜索入职文档"
"为登录问题创建错误工单"
"将 PROJ-123 的状态更新为“已完成”"
文档
完整文档可在 mcp-atlassian.soomiles.com 获取。
文档还提供 llms.txt 格式,LLM 可以轻松使用:
llms.txt— 文档站点地图llms-full.txt— 完整文档
主题 | 描述 |
uvx、Docker、pip、从源码 | |
API 令牌、PAT、OAuth 2.0 | |
IDE 设置、环境变量 | |
SSE、streamable-http、多用户 | |
所有 Jira 和 Confluence 工具 | |
常见问题和调试 |
兼容性
产品 | 部署 | 支持 |
Confluence | 云 | 完全支持 |
Confluence | 服务器/数据中心 | 支持(v6.0+) |
Jira | 云 | 完全支持 |
Jira | 服务器/数据中心 | 支持(v8.14+) |
主要工具
Jira | Confluence |
|
|
|
|
|
|
|
|
|
|
共 98 个工具 — 完整列表参见 工具参考。
安全
切勿共享 API 令牌。确保 .env 文件安全。参见 SECURITY.md。
贡献
开发设置参见 CONTRIBUTING.md。
许可证
MIT - 参见 LICENSE。非 Atlassian 官方产品。
Maintenance
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
- AlicenseNot gradedqualityDmaintenanceAn 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
- AlicenseNot gradedqualityCmaintenanceAn MCP server that integrates with Jira and Confluence to enable AI-powered issue management, content search, and document creation. It supports both Cloud and on-premise deployments, allowing users to automate workspace tasks through natural language.MIT
- AlicenseNot gradedqualityDmaintenanceA comprehensive MCP server for Atlassian Jira that enables AI assistants to manage issues, sprints, comments, and worklogs through natural language.MIT
- AlicenseBqualityAmaintenanceAn MCP server for integrating with Atlassian products including Confluence, Jira, Bitbucket, and Xray for Jira, enabling AI-powered operations like searching, creating, and updating issues, pages, and test results.7127MIT
Related MCP Connectors
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
MCP server for AI dialogue using various LLM models via AceDataCloud
An MCP server that integrates with Discord to provide AI-powered features.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/matutezam/atlassian-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server