{
  "markdown": "# Amplitude AI Plugin\n\nOfficial Amplitude plugin for AI coding tools. Turn your AI assistant into a product analyst — instrument analytics, analyze charts, run experiments, and understand users directly from your editor.\n\nWorks with **Claude Code**, **Cursor**, **Codex**, **Gemini CLI**, and **Claude**.\n\n---\n\n## Installation\n\n### Claude Code\n\n```\nclaude plugin install amplitude\n```\n\nOr from inside Claude Code:\n\n```\n/plugin install amplitude\n/reload-plugins\n```\n\nThen authenticate when prompted.\n\n### Cursor\n\nInstall from the [Cursor Marketplace](https://cursor.com/marketplace) or add manually in Cursor Settings > Plugins.\n\n### Codex\n\n1. Add the marketplace:\n    ```bash\n    codex plugin marketplace add amplitude/mcp-marketplace\n    ```\n\n2. Install the plugin from inside Codex:\n    ```\n    codex\n    # Then run /plugins, select Amplitude, and install\n    /plugins\n    ```\n\n### Gemini CLI\n\n```bash\ngemini extensions install https://github.com/amplitude/mcp-marketplace\n```\n\n---\n\n## Local development\n\nTo work on the plugin from a local checkout in Claude Code:\n\n```bash\ngit clone https://github.com/amplitude/mcp-marketplace\nclaude --plugin-dir ./mcp-marketplace/plugins/amplitude\n```\n\nThen run `/mcp` from inside Claude Code, select `plugin:amplitude:amplitude`, and follow the browser prompts to authenticate.\n\n---\n\n## What's Inside\n\n| Plugin | Description |\n| --- | --- |\n| [amplitude](./plugins/amplitude/) | Reusable analysis and instrumentation skills covering charts, dashboards, experiments, session replays, reliability, AI agent analytics, and analytics tracking workflows |\n\n---\n\n## Amplitude Plugin\n\nThe amplitude plugin turns your AI assistant into an expert product analyst and instrumentation partner. Skills are organized into seven areas:\n\n### Core Analytics\n\n| Skill | What it does |\n| --- | --- |\n| `create-chart` | Creates Amplitude charts from natural language descriptions |\n| `create-dashboard` | Builds dashboards from requirements, organizing charts into logical sections |\n| `analyze-chart` | Deep-dives a chart to explain trends, anomalies, and likely drivers |\n| `analyze-dashboard` | Reviews a dashboard end-to-end, surfacing key takeaways and areas of concern |\n\n### Product Insights\n\n| Skill | What it does |\n| --- | --- |\n| `analyze-experiment` | Designs A/B tests, monitors running experiments, and interprets results |\n| `monitor-experiments` | Triages all active and recently completed experiments by importance |\n| `analyze-feedback` | Synthesizes customer feedback into themes — feature requests, bugs, pain points, praise |\n| `analyze-account-health` | Summarizes B2B account health with usage patterns, risk signals, and expansion opportunities |\n| `discover-opportunities` | Finds product opportunities by cross-referencing analytics, experiments, replays, and feedback |\n| `compare-user-journeys` | Compares two user groups side-by-side to surface behavioral differences |\n\n### Session Replay & Debugging\n\n| Skill | What it does |\n| --- | --- |\n| `debug-replay` | Turns bug reports into numbered reproduction steps by extracting the interaction timeline from Session Replay |\n| `replay-ux-audit` | Watches multiple session replays for a flow and synthesizes a ranked friction map |\n| `diagnose-errors` | Triages product issues across network failures, JS errors, and error clicks |\n| `monitor-reliability` | Proactive reliability report from auto-captured error data so issues surface before users complain |\n\n### AI Agent Analytics\n\n| Skill | What it does |\n| --- | --- |\n| `analyze-ai-topics` | Analyzes what users ask AI agents about and how well each topic is served |\n| `investigate-ai-session` | Deep-dives specific AI agent sessions or failure patterns for root-cause analysis |\n| `monitor-ai-quality` | Delivers a proactive health report on AI agents covering quality, cost, performance, and errors |\n| `review-agent-insights` | Synthesizes recent results from Amplitude's AI agents into a unified, impact-ranked narrative |\n\n### Analytics Instrumentation\n\n| Skill | What it does |\n| --- | --- |\n| `diff-intake` | Reads a PR or branch diff and outputs a structured `change_brief` YAML for downstream skills |\n| `discover-event-surfaces` | From a change brief, lists candidate analytics events for PM prioritization |\n| `discover-analytics-patterns` | Maps how analytics is already implemented in the repo (SDK calls, naming, imports) |\n| `instrument-events` | From prioritized event candidates, builds a concrete instrumentation plan and JSON tracking plan |\n| `add-analytics-instrumentation` | End-to-end workflow — reads code, decides what to track, and produces a full instrumentation plan in one pass |\n| `taxonomy` | Source of truth for event taxonomy generation, data auditing, and governance best practices |\n\nA typical flow: `diff-intake` → `discover-event-surfaces` → `instrument-events`, with `discover-analytics-patterns` ensuring new tracking matches existing conventions.\n\n### Briefings\n\n| Skill | What it does |\n| --- | --- |\n| `daily-brief` | Morning briefing of the most important changes across your Amplitude instance |\n| `weekly-brief` | Weekly recap of trends, wins, and risks to share with your team or leadership |\n\n### Bonus\n\n| Skill | What it does |\n| --- | --- |\n| `what-would-lenny-do` | Answers product strategy questions by searching Lenny Rachitsky's archive (requires `lennysdata` MCP) |\n\n---\n\n## Repository Structure\n\n```text\n.agents/plugins/\n  marketplace.json            # Marketplace catalog (Codex)\n.claude-plugin/\n  marketplace.json            # Marketplace catalog (Claude Code)\n.cursor-plugin/\n  marketplace.json            # Marketplace catalog (Cursor) — kept in sync with .claude-plugin\nplugins/\n  amplitude/\n    .codex-plugin/\n      plugin.json             # Plugin manifest (Codex)\n    .claude-plugin/\n      plugin.json             # Plugin manifest (Claude Code)\n    .cursor-plugin/\n      plugin.json             # Plugin manifest (Cursor) — kept in sync with .claude-plugin\n    .mcp.json                 # MCP server config shared by Codex and other clients\n    skills/\n      add-analytics-instrumentation/\n      analyze-account-health/\n      analyze-ai-topics/\n      analyze-chart/\n      analyze-dashboard/\n      analyze-experiment/\n      analyze-feedback/\n      compare-user-journeys/\n      create-chart/\n      create-dashboard/\n      daily-brief/\n      debug-replay/\n      diagnose-errors/\n      diff-intake/\n      discover-analytics-patterns/\n      discover-event-surfaces/\n      discover-opportunities/\n      instrument-events/\n      investigate-ai-session/\n      monitor-ai-quality/\n      monitor-experiments/\n      monitor-reliability/\n      replay-ux-audit/\n      review-agent-insights/\n      taxonomy/\n      weekly-brief/\n      what-would-lenny-do/\n```\n\n---\n\n## Requirements\n\n- **MCP-compatible client** – Claude Code, Cursor, Codex, or Claude\n- **Amplitude account** with API access\n\n---\n\n## Contributing\n\nWe welcome contributions! Whether it's a new skill or improvement:\n\n1. Fork this repo\n2. Create a new branch for your feature\n3. Follow the existing patterns in `plugins/` for structure\n4. Submit a PR with a clear description\n\n---\n\n## Resources\n\n- [Amplitude Docs](https://amplitude.com/docs)\n- [MCP Protocol](https://modelcontextprotocol.io/)\n\n---\n\n## License\n\nMIT\n\n---\n\n## Support\n\n- **Issues**: [GitHub Issues](https://github.com/amplitude/mcp-marketplace/issues)\n- **Amplitude**: [amplitude.com](https://amplitude.com)\n",
  "bytes": 7439,
  "sha": "3feaa80094e131a194a6b38493aae9d8c9a895ea21b558c9b49ba6f1d256729d",
  "repo_slug": "amplitude/mcp-marketplace",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_amplitude_mcp_marketplace_amplitude_8f5e27f2/readme"
}