Bugsink MCP Server
Enables AI assistants to query and analyze errors from Bugsink self-hosted error tracking instances. Supports listing projects, teams, issues, and viewing detailed error events with stacktraces.
README
Bugsink MCP Server
A Model Context Protocol server for interacting with Bugsink error tracking via LLMs.
This server enables AI assistants like Claude, Cursor, and other MCP-compatible tools to query and analyze errors from your Bugsink instance.
Features
- List Projects - View all projects in your Bugsink instance
- List Teams - View all teams
- List Issues - Query grouped error occurrences by project
- Get Issue Details - Retrieve detailed issue information
- List Events - View individual error occurrences with stacktraces
- Get Event Details - Full event data including tags and contexts
- Test Connection - Verify API connectivity
Installation
Via npx (Recommended)
npx bugsink-mcp
Global Install
npm install -g bugsink-mcp
From Source
git clone https://github.com/j-shelfwood/bugsink-mcp.git
cd bugsink-mcp
npm install
npm run build
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
BUGSINK_URL |
Yes | Your Bugsink instance URL (e.g., https://error-tracking.example.com) |
BUGSINK_TOKEN |
Yes | API token for authentication |
Generating an API Token
# Via Bugsink management command
bugsink-manage create_auth_token
Or through the Bugsink web UI under Settings > API Tokens.
MCP Client Configuration
Claude Desktop
Add to your Claude Desktop configuration (~/.claude/claude_desktop_config.json):
{
"mcpServers": {
"bugsink": {
"command": "npx",
"args": ["bugsink-mcp"],
"env": {
"BUGSINK_URL": "https://your-bugsink-instance.com",
"BUGSINK_TOKEN": "your-api-token"
}
}
}
}
Claude Code CLI
claude mcp add bugsink -- npx bugsink-mcp
Then set environment variables in your shell or .env file.
Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"bugsink": {
"command": "npx",
"args": ["bugsink-mcp"],
"env": {
"BUGSINK_URL": "https://your-bugsink-instance.com",
"BUGSINK_TOKEN": "your-api-token"
}
}
}
}
Available Tools
test_connection
Test connectivity to your Bugsink instance.
list_projects
List all projects in the Bugsink instance.
get_project
Get detailed information about a specific project including DSN.
Parameters:
project_id(number, required): The project ID
list_teams
List all teams in the Bugsink instance.
list_issues
List issues for a specific project.
Parameters:
project_id(number, required): The project IDstatus(string, optional): Filter by status ('unresolved', 'resolved', 'muted')limit(number, optional): Max results (default: 25)
get_issue
Get detailed information about a specific issue.
Parameters:
issue_id(number, required): The issue ID
list_events
List events (individual error occurrences) for a specific issue.
Parameters:
issue_id(number, required): The issue IDlimit(number, optional): Max results (default: 10)
get_event
Get detailed event information including full stacktrace.
Parameters:
event_id(string, required): The event ID
Example Usage
Once configured, you can ask your AI assistant:
- "List all projects in Bugsink"
- "Show me the latest issues for project 1"
- "What's the stacktrace for issue #42?"
- "Get the details of the most recent error event"
Development
# Install dependencies
npm install
# Run in development mode
npm run dev
# Build for production
npm run build
# Run tests
npm test
API Compatibility
This server is designed for Bugsink, a self-hosted error tracking platform. Bugsink uses its own REST API (/api/canonical/0/) which is different from Sentry's API.
Note: This server does NOT work with Sentry or Sentry-hosted services. For Sentry, use the official sentry-mcp server.
License
MIT
Contributing
Contributions welcome! Please open an issue or PR on GitHub.
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。