The Lindo MCP Server provides a universal interface for AI tools to interact with your Lindo workspace. It works with Claude, ChatGPT, Perplexity, Cursor, VS Code, Windsurf, and any MCP-compatible client.Documentation Index
Fetch the complete documentation index at: https://lindo.ai/docs/llms.txt
Use this file to discover all available pages before exploring further.
What is MCP?
The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources. Lindo’s MCP server exposes 43 tools for managing websites, pages, blogs, clients, and credits.One-Click Install
Install in Cursor
Click to add Lindo MCP to Cursor automatically.
Install in VS Code
Click to add Lindo MCP to VS Code automatically.
Add to Claude
Add as a connector in Claude.ai settings.
Installation
Remote Server (Recommended)
Use the hosted MCP server with OAuth login. Works with Claude.ai connectors, ChatGPT Apps, and more.Local Server (npx)
Run the MCP server locally. First run opens a browser for login, or set theLINDO_API_KEY environment variable.
Configuration by Client
- Cursor
- VS Code
- Claude Desktop
- Claude Code
- Windsurf
- Perplexity
Add to
.cursor/mcp.json:Authentication
The MCP server supports two authentication methods:- Browser login — On first run, the server opens a browser window for OAuth login. Credentials are cached locally.
- API key — Set the
LINDO_API_KEYenvironment variable to skip the browser flow.
Available Tools (43)
The MCP server exposes tools organized into these groups:| Group | Tools | Description |
|---|---|---|
| Workspace | 6 | Get workspace info, settings, analytics |
| Clients | 6 | Create, list, update, delete clients, generate magic links |
| Websites | 10 | Create, list, update, delete, publish, configure websites |
| Pages | 9 | Create, list, update, delete, publish pages |
| Blogs | 9 | Create, list, update, delete, publish blog posts |
| Credits | 3 | Check balance, allocate, view history |
Example: Create a Website
When connected to an AI assistant, you can say:“Create a website for a coffee shop called Bean & Brew in Portland”The AI will use the
create_website tool with the appropriate parameters.
Example: Manage Clients
“Create a client for john@example.com and assign them 500 credits”The AI will call
create_client followed by allocate_credits.
Troubleshooting
Server not connecting
Server not connecting
- Ensure Node.js 18+ is installed
- Try running
npx -y @lindoai/mcp-serverdirectly in your terminal to check for errors - Verify your API key is valid
Authentication issues
Authentication issues
- If browser login fails, use the API key method instead
- Ensure your API key starts with
lindo_sk_ - Check that your workspace plan supports API access
Tools not appearing
Tools not appearing
- Restart your AI client after adding the MCP configuration
- Check the MCP configuration file path is correct for your client
- Verify the server is running by checking your client’s MCP status panel

