# Lovable

> Lovable MCP tool usage — deploy projects, message agent, test with agent-browser. Minimize credits by delegating to local repo.

- Skill: `x-cmd/lovable` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add x-cmd/lovable`
- Raw SKILL.md: https://api.skillmd.com/api/skills/x-cmd/lovable/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra, AI & ML
- Author: x-cmd (https://skillmd.com/u/x-cmd)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/x-cmd/lovable

---



# Lovable

## Setup & full MCP reference

```
claude mcp add --transport http lovable "https://mcp.lovable.dev"
```

Full MCP reference: [lovable-mcp-server.md](https://docs.lovable.dev/integrations/lovable-mcp-server.md).

- Plan — Pro/Business required
- Auth — OAuth browser prompt on first call
- Clients — Claude Code, Claude Desktop, ChatGPT, Cursor, VS Code

## Core workflow: local first, save credits

```
local edit → npm run dev (verify) → git push → mcp__lovable__deploy_project → agent-browser test
```

## Rules

- **MUST verify project ID** — call `list_projects query=<name>` to confirm the correct `project_id` before any action. **NEVER reuse an ID from memory or previous context.** After deploy, wait 30s then verify the live site before reporting success.
- **MUST screenshot before & after** — when modifying a project, capture a before-screenshot, make changes, capture an after-screenshot. Compare to confirm intent. Post to GitHub issue when applicable. **Scrub all privacy data** (tokens, personal info, emails) before uploading.

## Common MCP calls

```
mcp__lovable__list_workspaces
mcp__lovable__list_projects  workspace_id=<id>  query=<name>
mcp__lovable__get_project  project_id=<id>
mcp__lovable__deploy_project  project_id=<id>
mcp__lovable__send_message  project_id=<id>  message="<instruction>"  wait=true
mcp__lovable__get_diff  project_id=<id>  message_id=<msg_id>
```

## Usecase — Analytics

Quick overview: `list_projects publish_status=published` returns visitor counts per project.
Export as TSV/CSV with schema: `id, project, 24h, 7d, 30d, URL`.

For detailed analytics (pageviews, bounce rate, traffic sources, devices), see [ANALYTICS.md](ANALYTICS.md).

## Usecase — Knowledge (persisted instructions for Lovable agent)

```
mcp__lovable__get_project_knowledge  project_id=<id>
mcp__lovable__set_project_knowledge  project_id=<id>  content="<markdown>"
```
Always `get` before `set` — replaces entirely. Max 10K chars. Also: `get/set_workspace_knowledge`.

## Test with agent-browser

```
agent-browser --profile /tmp/ab-default open <url> --session <proj>-mobile --headed
agent-browser --session <proj>-mobile set device "iPhone 14"
agent-browser --session <proj>-mobile snapshot -i
```
Full usage: see skill0 `agent-browser`.

## Troubleshooting

- Site not updated — `deploy_project`
- Code change, local exists — Local → push → deploy
- Code change, no local — `send_message` (high credit cost)
- Mobile test — `agent-browser set device "iPhone 14"`

For PWA issues, sync problems, and more, see [TROUBLESHOOTING.md](TROUBLESHOOTING.md).

## For more information

- [docs llms.txt](https://docs.lovable.dev/llms.txt) — full documentation index
- [lovable.dev llms.txt](https://lovable.dev/llms.txt) — product hub, pricing, guides, templates
- [Integrations](https://docs.lovable.dev/integrations/introduction.md) — Stripe, Supabase, Slack, etc.
- [Chat connectors](https://docs.lovable.dev/integrations/mcp-servers.md) — bring Notion, Linear, Jira into builds
- [Lovable API](https://docs.lovable.dev/integrations/lovable-api.md) — build apps programmatically via REST

## Related

- [agent-browser](../../it/agent-browser/SKILL.md) — verification flow
- [prompt](../prompt/SKILL.md) — communicating with the agent
- [devloop](../devloop/SKILL.md) — lovable projects follow devloop shape