About Lovable
Lovable’s official MCP server lets MCP-compatible clients manage Lovable projects through natural-language requests. It covers project creation and deployment as well as code inspection, database operations, integrations, and analytics.
Key features
- 01Create, edit, deploy, and manage projects
- 02Message project AI agents
- 03Inspect diffs, files, and edit history
- 04Manage project instructions and databases
- 05Configure integrations and MCP servers
- 06Review project traffic analytics
Use cases
- 01Build and deploy an app from an MCP client
- 02Review generated code changes and files
- 03Run SQL against a project database
- 04Connect external services to a project
MCP support
Exposes Lovable project and workspace operations as tools to MCP clients over Streamable HTTP. Authentication uses OAuth 2.1.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.lovable.devclaude mcp add --transport http dev-lovable https://mcp.lovable.dev{"mcpServers":{"dev-lovable":{"type":"http","url":"https://mcp.lovable.dev"}}}Open in Cursor{"servers":{"dev-lovable":{"type":"http","url":"https://mcp.lovable.dev"}}}Open in VS Code{"mcpServers":{"dev-lovable":{"type":"http","url":"https://mcp.lovable.dev"}}}{"mcpServers":{"dev-lovable":{"serverUrl":"https://mcp.lovable.dev"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMELovable MCP
The official Model Context Protocol server for Lovable, an AI-powered full-stack app builder.
Connect Claude, Cursor, Codex, and other MCP-compatible clients to Lovable so they can create, edit, deploy, and manage Lovable projects through natural language.
Endpoint
https://mcp.lovable.dev
Transport: Streamable HTTP.
Authentication
OAuth 2.1. MCP clients discover the authorization server via RFC 9728 metadata at https://mcp.lovable.dev/.well-known/oauth-protected-resource and obtain a bearer token automatically. The token is passed as Authorization: Bearer <token>.
Install
Claude, Claude Code, and ChatGPT need only the URL. Any other client must also pass Lovable's public OAuth client ID (6d465f583e1e4ce5801b1616f735670c), shown below.
Claude Code
claude mcp add --transport http lovable https://mcp.lovable.dev
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"lovable": {
"type": "http",
"url": "https://mcp.lovable.dev"
}
}
}
ChatGPT
Add the URL directly — no client ID needed:
https://mcp.lovable.dev
Cursor / Windsurf
Add to your client's MCP config (~/.cursor/mcp.json, or Windsurf's mcp_config.json):
{
"mcpServers": {
"lovable": {
"type": "http",
"url": "https://mcp.lovable.dev",
"auth": {
"CLIENT_ID": "6d465f583e1e4ce5801b1616f735670c"
}
}
}
}
VS Code
{
"servers": {
"lovable": {
"type": "http",
"url": "https://mcp.lovable.dev",
"auth": {
"CLIENT_ID": "6d465f583e1e4ce5801b1616f735670c"
}
}
}
}
Codex CLI
codex mcp add lovable --url https://mcp.lovable.dev
codex mcp login lovable
Other clients
Use the same type: http + url + auth.CLIENT_ID shape as the Cursor example above.
Tools
The server exposes tools across these areas:
- Projects & workspaces — list, create, deploy, remix, inspect; manage visibility
- Agent interaction — send messages to a project's AI agent and retrieve responses
- Code inspection — diffs, file tree, file contents, edit history
- Knowledge — read and write project / workspace AI instructions
- Cloud database — enable a Postgres database, check status, run SQL, get connection info
- Connectors & MCP servers — list, add, and remove external integrations (Linear, Notion, Slack, custom MCP, …)
- Templates & libraries — browse template and library projects
- Analytics — historical and real-time project traffic
- File uploads — generate upload URLs for attaching images
Heads up:
create_projectandsend_messageconsume Lovable build credits.deploy_projectpublishes a public URL.query_databaseruns SQL directly against your project's database.
See the Lovable MCP documentation for the full tool reference.
Common workflow
Build and deploy a new app:
1. list_workspaces() → workspace_id
2. create_project(workspace_id, ...) → project_id (uses credits)
3. send_message(project_id, "Add ...") → message_id (uses credits)
4. get_diff(project_id, message_id) → review changes
5. deploy_project(project_id) → live URL
Most tools need a workspace_id — call list_workspaces first. read_file needs a git ref; get latest_commit_sha from get_project.
Troubleshooting
| Symptom | Fix |
|---|---|
401 Unauthorized / expired token | Re-run your client's login flow to refresh the OAuth token |
| OAuth window loops or never completes | Confirm the client passes the auth.CLIENT_ID shown above |
| "Transport not supported" | The client must support Streamable HTTP |
Tool fails on a missing workspace_id | Call list_workspaces first and pass the returned ID |
Registry
This repository hosts the server.json entry for the MCP registry.
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.