{
  "markdown": "# Lightup\n\nConnect Lightup to MCP-compatible AI agents.\n\nThis repository is the entry point for using Lightup inside agentic workflows. Client-specific setup lives in dedicated folders so the structure stays stable as support expands across interfaces.\n\n## Quick Start\n\nUse the repo-level setup wrapper and pass the client you want to configure:\n\n```bash\ncurl -sL https://raw.githubusercontent.com/lightup-data/lightup/main/setup.sh \\\n  | bash -s -- claude\n```\n\n```bash\ncurl -sL https://raw.githubusercontent.com/lightup-data/lightup/main/setup.sh \\\n  | bash -s -- gemini\n```\n\nThe setup flow automatically looks for `lightup-api-credential*.json` in common locations such as `~/Downloads`. If multiple files are found it picks the most recently modified one and warns you. If no file is found, the script will ask whether you have a Lightup account — if not, it walks you through signing up for a 30-day free trial at [my.lightup.ai](https://my.lightup.ai).\n\nTo use a specific credential file, pass the path explicitly:\n\n```bash\ncurl -sL https://raw.githubusercontent.com/lightup-data/lightup/main/setup.sh \\\n  | bash -s -- claude /path/to/lightup-api-credential.json\n```\n\nClient-specific installation and usage details live in the dedicated guides below.\n\n## Claude Code Plugin (Alternative to setup.sh)\n\nIf you use [Claude Code](https://docs.anthropic.com/en/docs/claude-code), you can install Lightup as a **Claude Code plugin** instead of running the setup script. The plugin auto-discovers your `lightup-api-credential.json`, connects automatically, and adds built-in slash commands and a specialized data quality agent — no credential prompts.\n\n```bash\nclaude plugin marketplace add lightup-data/lightup\nclaude plugin install lightup-ai@lightup\n```\n\nThe plugin finds your credential file in `~/Downloads`, `~/Desktop`, or `~` automatically. See [lightup-ai-plugin/README.md](./lightup-ai-plugin/README.md) for full details.\n\n## Gemini CLI Extension (Alternative to setup.sh)\n\nIf you use [Gemini CLI](https://github.com/google-gemini/gemini-cli), you can install Lightup as a **Gemini CLI extension** instead of running the setup script. The extension auto-discovers your `lightup-api-credential.json`, connects automatically, and adds a specialized data quality agent — no credential prompts.\n\n```bash\ngemini extensions install https://github.com/lightup-data/lightup\n```\n\nThe extension finds your credential file in `~/Downloads`, `~/Desktop`, or `~` automatically. See [lightup-gemini-plugin/README.md](./lightup-gemini-plugin/README.md) for full details.\n\n## Available Guides\n\n- [Claude Code](./claude/README.md)\n- [Gemini CLI](./gemini-cli/README.md)\n- <sub>Codex CLI (coming soon)</sub>\n\n## Why This Repo Exists\n\nLightup helps teams bring trusted data quality context into the tools they already use to investigate issues, debug pipelines, and answer operational questions. This repo packages client-specific setup instructions and scripts in one place, starting with Claude Code and designed to extend cleanly to additional AI agent clients over time.\n\n## Current Support\n\n- Claude Code: available now\n- Gemini CLI: available now\n- Codex CLI: coming soon\n\n## Setup Model\n\nEach client guide is responsible for its own installation and connection flow. That keeps the top-level repository product-oriented, while letting each integration evolve independently.\n\nPick the guide for your preferred AI client to get started.\n\n---\n\n## What is Lightup Agentic\n\nLightup Agentic exposes your Lightup data quality platform as an MCP (Model Context Protocol) server — letting any MCP-compatible AI agent read metrics, monitor data quality, diagnose incidents, and create new monitors in plain English, without leaving your AI tool.\n\n```\n┌─────────────────────┐        MCP (SSE)        ┌─────────────────────┐\n│   AI Agent Client   │ ◄─────────────────────► │  Lightup MCP Server │\n│                     │                          │                     │\n│  • Claude Code      │                          │  Exposes 41 tools   │\n│  • Gemini CLI       │                          │  for metrics,       │\n│  • Codex CLI        │                          │  monitors,          │\n│                     │                          │  incidents, docs    │\n│                     │                          └──────────┬──────────┘\n└─────────────────────┘                                     │\n                                                       REST API\n                                                            │\n                                               ┌────────────▼───────────┐\n                                               │   Lightup Platform     │\n                                               │   (your instance)      │\n                                               └────────────────────────┘\n```\n\n---\n\n## Prerequisites\n\n| Requirement | Details |\n|---|---|\n| AI client | Claude Code, Gemini CLI, or Codex CLI |\n| Lightup account | An active Lightup instance with at least Viewer access, or sign up for a [30-day free trial](https://my.lightup.ai) |\n| API credential file | Download from Lightup UI → Profile → API Credentials → Download (setup will guide you if you don't have one yet) |\n| Network access | Your machine must be able to reach the Lightup MCP server URL (provided by your Lightup team) |\n\n---\n\n## What You Can Ask\n\n### Read — Explore your data quality\n\n| Question | What it does |\n|---|---|\n| \"How many metrics do we have?\" | Count metrics across all workspaces |\n| \"List my workspaces\" | Show all workspaces you have access to |\n| \"Show all metrics in workspace Acme\" | List metrics in a specific workspace |\n| \"What monitors are failing in workspace Acme?\" | Show monitors in error state |\n| \"List recent incidents\" | Show data quality incidents from the last 7 days |\n| \"Show all datasources in workspace Acme\" | List connected data sources |\n| \"Give me a health summary of workspace Acme\" | Compact overview of metrics, monitors, incidents |\n| \"What's the overall platform status?\" | Cross-workspace rollup for the entire instance |\n\n### Diagnose — Understand what's wrong\n\n| Question | What it does |\n|---|---|\n| \"Diagnose monitor `<uuid>`\" | Explains in plain English why a monitor is not working |\n| \"Why is monitor `<name>` getting false positives?\" | Root cause analysis |\n| \"Get details for incident `<uuid>`\" | Full incident breakdown |\n| \"Show system errors in workspace Acme from last 48 hours\" | Recent platform events |\n\n### Write — Create and configure\n\n| Question | What it does |\n|---|---|\n| \"Create a null check on the orders table\" | Creates a null fraction metric + monitor |\n| \"Create a row count metric on the customers table\" | Creates a data volume metric |\n| \"Create an anomaly detection monitor on metric X\" | Sets up ML-based monitoring |\n| \"Create a manual threshold monitor with bounds 0 to 500\" | Sets up fixed threshold monitoring |\n| \"Create a postgres datasource in workspace Acme\" | Connects a new database |\n| \"Create a workspace called Production\" | Creates a new workspace |\n\n### Learn — Documentation\n\n| Question | What it does |\n|---|---|\n| \"What is Lightup?\" | Overview of the platform |\n| \"What is a slice?\" | Explains metric slicing |\n| \"How does anomaly detection work?\" | Explains ML-based monitoring |\n| \"What metric types are available?\" | Lists all metric types with descriptions |\n| \"How does monitor training work?\" | Explains the training lifecycle |\n\n---\n\n## Available Tools\n\n### Summary Tools (token-efficient)\n\n| Tool | Description |\n|---|---|\n| `count_all_metrics` | Total metric count across all workspaces |\n| `count_all_monitors` | Monitor count with live / training / paused / error breakdown |\n| `count_all_incidents` | Total incident count (configurable lookback window) |\n| `get_workspace_health` | Compact health summary for one workspace |\n| `get_platform_summary` | Cross-workspace rollup for the entire Lightup instance |\n\n### Workspace & Datasource Tools\n\n| Tool | Description |\n|---|---|\n| `list_workspaces` | List all workspaces |\n| `get_workspace` | Get workspace details |\n| `create_workspace` | Create a new workspace |\n| `list_datasources` | List datasources in a workspace |\n| `get_datasource` | Get datasource details |\n| `create_datasource` | Create a new datasource |\n| `test_datasource_connection` | Test a datasource connection before creating |\n\n### Metric Tools\n\n| Tool | Description |\n|---|---|\n| `list_metrics` | List metrics in a workspace |\n| `get_metric` | Get metric details |\n| `search_metric` | Search for a metric by name across workspaces |\n| `create_metric` | Create a new metric |\n| `create_metrics_batch` | Create multiple metrics at once |\n| `update_metric` | Update an existing metric |\n| `delete_metric` | Delete a metric |\n| `explore_metric_target` | Explore available tables and columns for a metric |\n| `analyze_table` | Analyze a table's structure and data profile |\n| `suggest_metrics` | Get AI-generated metric suggestions for a table |\n| `preview_metric` | Preview metric results before creating |\n| `validate_custom_sql` | Validate custom SQL before using in a metric |\n\n### Monitor Tools\n\n| Tool | Description |\n|---|---|\n| `list_monitors` | List monitors in a workspace |\n| `get_monitor` | Get monitor details |\n| `create_monitor` | Create a threshold or anomaly detection monitor |\n| `update_monitor` | Update an existing monitor |\n| `delete_monitor` | Delete a monitor |\n| `diagnose_monitor` | Explain why a monitor is not working |\n\n### Incident & Event Tools\n\n| Tool | Description |\n|---|---|\n| `list_incidents` | List recent incidents in a workspace |\n| `get_incident` | Get incident details |\n| `list_events` | List system events (errors, warnings) |\n| `list_recommendations` | AI-generated metric/monitor recommendations |\n\n### Integration & User Tools\n\n| Tool | Description |\n|---|---|\n| `list_integrations` | List integrations (Slack, PagerDuty, email, etc.) |\n| `list_users` | List all users with roles and workspace memberships |\n| `list_llm_connections` | List LLM connections configured in the instance |\n| `list_catalog_integrations` | List catalog integrations (Atlan, Alation) |\n\n### Documentation Tools\n\n| Tool | Description |\n|---|---|\n| `get_documentation` | Fetch Lightup product documentation by topic |\n| `list_documentation_topics` | List all available documentation topics |\n\n---\n\n## How It Works\n\nThe Lightup MCP server is **stateless**. Each connection carries its own credentials in the URL — no credentials are stored server-side.\n\n```\nYour AI client connects with:\n  /sse?host=https://app.acme.lightup.ai&refresh_token=eyJ...\n         │                                      │\n         ▼                                      ▼\n  Your Lightup instance URL         Your JWT refresh token\n  (which Lightup instance to use)   (your identity)\n```\n\nEvery session is fully isolated — the server only sees and accesses your Lightup instance using your credentials. No data is shared across sessions.\n\n**Security:** Credentials travel over HTTPS only and are never logged or stored on the MCP server.\n\n---\n\n## Troubleshooting\n\n| Problem | Solution |\n|---|---|\n| `Token refresh failed` | Download a new credential file from Lightup UI and re-run setup |\n| `Connection refused` | Verify the MCP server URL is reachable. Check firewall / VPN. |\n| Tools not appearing in AI client | Exit and start a new session |\n| `HTTP 403` on tool calls | Your Lightup user may lack access to that workspace. Contact your admin. |\n| Wrong workspace data | Verify the `host` in your credential file matches your Lightup instance |\n",
  "bytes": 11564,
  "sha": "8c4c0b82aae047eb309967c77616cbf9cff3cd35281b729a097706e6a8dd9cf4",
  "repo_slug": "lightup-data/lightup",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_lightup_data_lightup_f432200e/readme"
}