
GitHub-Jira MCP Server
Enables secure integration between GitHub and Jira with permission controls, allowing users to manage repositories, create issues and pull requests, and handle Jira project workflows through natural language. Supports OAuth authentication and comprehensive security enforcement for both platforms.
README
GitHub-Jira MCP Server
A comprehensive Model Context Protocol (MCP) server that provides secure integration between GitHub and Jira with proper permission controls and security enforcement.
🛠️ Installation
Prerequisites
- Python 3.11+
- GitHub Personal Access Token
- Jira OAuth App Credentials
Setup
-
Clone the repository
git clone <your-repo> cd mcp-servers
-
Install dependencies
uv sync
-
Configure environment variables
cp env.example .env # Edit .env with your actual credentials
-
Set up credentials
GitHub:
- Go to GitHub Settings > Tokens
- Generate a new personal access token
- Required scopes:
repo
(for private repos),public_repo
(for public repos)
Jira:
- Go to Atlassian Developer Console
- Create a new OAuth app
- Set redirect URI to:
http://localhost:8080/callback
- Note your Jira instance URL, client ID, and client secret
🔧 Configuration
Environment Variables
Create a .env
file in your project root:
# GitHub Configuration
GITHUB_TOKEN=ghp_your_github_token_here
# Jira OAuth Configuration
JIRA_URL=https://your-domain.atlassian.net
JIRA_CLIENT_ID=your_jira_oauth_client_id_here
JIRA_CLIENT_SECRET=your_jira_oauth_client_secret_here
# Optional: Jira Access Tokens (will be obtained automatically via OAuth)
JIRA_ACCESS_TOKEN=
JIRA_REFRESH_TOKEN=
# Optional: Logging
LOG_LEVEL=INFO
MCP Client Configuration
Add this to your MCP client configuration:
{
"mcpServers": {
"github-jira": {
"command": "python",
"args": ["mcp_github_jira_server.py"],
"env": {
"GITHUB_TOKEN": "your_token_here",
"JIRA_URL": "https://your-domain.atlassian.net",
"JIRA_CLIENT_ID": "your_jira_oauth_client_id_here",
"JIRA_CLIENT_SECRET": "your_jira_oauth_client_secret_here"
}
}
}
}
📚 Usage
Starting the Server
python mcp_github_jira_server.py
Available Tools
GitHub Tools
github_read_file(owner, repo, path)
- Read file content with security checksgithub_create_issue(owner, repo, title, body, labels)
- Create issues in own reposgithub_create_pull_request(owner, repo, title, body, head, base)
- Create PRs in own reposgithub_delete_file(owner, repo, path, message, sha)
- Delete files from own reposcheck_github_permissions()
- Check current GitHub permissions
Jira Tools
jira_create_issue(project_key, summary, description, issue_type)
- Create issuesjira_search_issues(jql, max_results)
- Search issues using JQLjira_update_issue(issue_key, updates)
- Update issue fieldsjira_add_comment(issue_key, comment)
- Add comments to issuesjira_transition_issue(issue_key, transition_id)
- Move issues through workflowscheck_jira_permissions()
- Check current Jira permissionssetup_jira_oauth()
- Setup Jira OAuth authentication
Available Resources
GitHub Resources
github://{owner}/{repo}
- Repository informationgithub://{owner}/{repo}/files/{path}
- File content
Jira Resources
jira://projects/{project_key}
- Project informationjira://issues/{issue_key}
- Issue details
Available Prompts
check_repository_security_permissions
- Check GitHub permissionsread_file_from_github_repo
- Read files from GitHubcreate_jira_issue_in_project
- Create Jira issuesupdate_jira_issue_workflow
- Update workflow statesgithub_repository_management
- Manage GitHub reposjira_project_workflow_management
- Manage Jira projectssetup_jira_oauth_authentication
- Setup Jira OAuth authentication
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。