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 execution duration, count executions, and collect numeric runtime metrics directly from the AI workflow.
概览
Lightrun AI
A collection of reusable skills for investigating runtime issues with Lightrun.
What is in this repository
skills/— skill folders (SKILL.md, plus optional assets/scripts).cursor-plugin/— Cursor plugin metadata.claude-plugin/— Claude plugin metadata.cursor/mcp.json— Cursor MCP server configuration used by the plugin metadata
Available skills
lightrun-live-runtime-debugging— deterministic live-runtime investigation workflow with preflight checks, evidence capture, and handoff output.
Installation
Cursor
- Open Cursor.
- Add plugin from repository URL (or local path).
- Use this repository URL:
https://github.com/lightrun-platform/lightrun-ai
Claude
This repository includes:
.claude-plugin/plugin.json.claude-plugin/marketplace.json
Use your Claude plugin/marketplace flow to install from this repository.
Codex
Codex loads skills from .agents/skills locations.
- Copy or symlink skill folders from
skills/into one of:$REPO_ROOT/.agents/skills$HOME/.agents/skills
- Restart/reload Codex if needed.
Requirements
- Access to Lightrun MCP server
- Completed MCP OAuth authorization for your environment
Contributing
- Add a new folder under
skills/<skill-name>/. - Add
SKILL.mdwith YAML frontmatter (name,description). - Add optional assets/scripts if needed.
- Update marketplace/plugin metadata when adding publishable skills.
服务器配置
{
"mcpServers": {
"Lightrun": {
"url": "https://app.lightrun.com/mcp"
}
}
}