Connect Claude to Lovable
Build and change Lovable apps, run SQL on their Cloud database, read their code, and publish them. Toolspoke puts 1 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.
- Connection
- Remote MCP server
- Authentication
- Lovable OAuth
- Actions exposed
- 1
- What a call bills
- Nothing
- Adapter
- Maintained by Toolspoke
- Category
- Developer tools
Connected in three steps
Install Lovable
Open the marketplace in your workspace, add Lovable to the project your agents work in, and it appears on the gateway immediately.
Connect the credential
Sign in to Lovable. Toolspoke holds the token encrypted and refreshes it when it expires.
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.
.mcp.json{
"mcpServers": {
"toolspoke": {
"type": "http",
"url": "https://toolspoke.com/mcp"
}
}
}One block covers every tool you have installed. Lovable shows up in the client as soon as your policy allows it, and so does everything else you install later.
Where the address goes, per client
- Claude Code
Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp- Claude and Claude Desktop
Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp- Cursor
~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }- Codex
~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"- VS Code
.vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }
What Lovable asks for
Press connect and sign in to Lovable. Toolspoke keeps the token encrypted and refreshes it when it expires, so there is nothing to copy and nothing to rotate by hand.
The scopes it asks for
- offline
- projects:read
- projects:write
- workspaces:read
- workspaces:write
What Claude can do in Lovable
1 actions, each one declared by name in the connector. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.
1 read, none write, none destructive
Reads
1Fetches data and changes nothing.
get_meWho the signed-in Lovable account is. Free, and takes no input.
What it will not do
The gateway enforces each of these, so they can be stated flatly.
- It cannot call anything else
- The 1 actions above are the whole of it. A call to any other name is refused before it reaches Lovable rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
- It only reads
- Every action here reads. Nothing this connector can do changes anything in Lovable.
- It reaches no further than your credential
- Toolspoke holds no access to Lovable of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
- It never hears from Lovable
- Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Lovable. An agent has to ask.
- It does not smooth over provider limits
- Toolspoke does not retry, queue or back off around Lovable's own rate limits. A call that Lovable refuses comes back to the agent as a failed call.
Before you connect it
What can Claude do in Lovable?
1 named actions: 1 that only read. They include get_me. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.
What credentials does the Lovable connector need?
Nothing to paste. You sign in to Lovable over OAuth 2.0 and Toolspoke keeps the resulting token encrypted, refreshing it when it expires. It asks for offline, projects:read, projects:write, workspaces:read and workspaces:write, and can do nothing outside them.
Does the Lovable connector work with Cursor and Codex, or only Claude?
Any client that speaks MCP, and every one of them gets the same 1 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.
What does the Lovable connector not do?
The 1 actions above are the whole of it. A call to any other name is refused before it reaches Lovable rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Every action here reads. Nothing this connector can do changes anything in Lovable. Toolspoke holds no access to Lovable of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Lovable. An agent has to ask. Toolspoke does not retry, queue or back off around Lovable's own rate limits. A call that Lovable refuses comes back to the agent as a failed call.
Can I limit which actions an agent can call?
Yes, in two places. The project switches Lovable's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.
What gets recorded when an agent calls Lovable?
Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.
More developer tools connectors
Browse all of themConnect Claude to Lovable
Add Lovable to a project and point your client at the gateway.