Lightrun MCP Server
@lightrun-platform
关于 Lightrun MCP Server
Lightrun MCP connects AI coding assistants to live runtime context from production and staging applications for safe code-level debugging without redeploying. It lets MCP-compatible clients discover runtime sources, inspect live expression values, capture call stacks, measure exe
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"Lightrun": {
"url": "https://app.lightrun.com/mcp"
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Lightrun MCP Server?
Lightrun MCP Server is an MCP-compatible server that provides reusable skills for investigating runtime issues with Lightrun. It integrates with Lightrun’s platform to enable deterministic live‑runtime debugging workflows, and is intended for developers using AI coding assistants like Cursor, Claude, or Codex.
How to use Lightrun MCP Server?
Access Lightrun MCP Server by installing the Lightrun AI repository through your AI assistant’s plugin or marketplace flow. For Cursor, add the plugin from the repository URL https://github.com/lightrun-platform/lightrun-ai. For Claude, use the included .claude-plugin/ metadata. For Codex, copy or symlink skill folders from skills/ into .agents/skills. Complete MCP OAuth authorization for your environment before use.
Key features of Lightrun MCP Server
- Deterministic live‑runtime investigation workflow
- Preflight checks and evidence capture
- Handoff output for issue resolution
- Works with Cursor, Claude, and Codex
- Access requires Lightrun MCP OAuth authorization
Use cases of Lightrun MCP Server
- Debugging live applications in production without stopping them
- Collecting evidence during runtime investigation
- Handing off investigation results to team members
FAQ from Lightrun MCP Server
What does Lightrun MCP Server do?
It provides a reusable skill for deterministic live‑runtime debugging, including preflight checks, evidence capture, and handoff output, all accessed through an MCP server.
What dependencies or runtime requirements are needed?
You need access to the Lightrun MCP server and must have completed MCP OAuth authorization for your environment. No other runtime dependencies are listed.
Where do the skills live?
Skills are stored in folders under the skills/ directory in the repository, each with a SKILL.md and optional assets/scripts.
How is authentication handled?
Authentication is via MCP OAuth authorization; you must complete that flow for your environment before using the server.
What transports or auth methods are supported?
The README only mentions MCP OAuth authorization; no specific transport protocols are detailed.
其他 分类下的更多 MCP 服务器
MCP Go 🚀
mark3labsA Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Production-ready MCP integrations for AI applications
Klavis-AIKlavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
ICSS
chokcoco不止于 CSS
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
评论