Connecting Lemonado MCP to Claude

Lane Goedhart
Anthropic’s Claude supports remote Model Context Protocol (MCP) servers, allowing users to connect external tools and data sources directly through custom connectors. This means Claude can securely access live business data inside business tools, databases, and spreadsheets directly from the chat interface.
Many MCP servers support both read and write functions, allowing models to query data and perform actions within connected systems. While this opens up powerful new capabilities, it also introduces potential risks — such as unverified connectors that could alter or delete data.
Lemonado, by contrast, operates as a remote read-only MCP server. It can securely access and analyze your connected data sources (like Stripe, Google Ads, Sheets, or Postgres) without ever modifying them. This design ensures data integrity and safety while still giving Claude advanced analytical power and SQL translation through natural language queries.
This guide walks you through adding Lemonado as a custom connector in Claude and running your first test query. It assumes you’ve already created your Lemonado account and connected one or more data sources in your workspace.
Step 1 — Open Connector Settings
Go to claude.ai in your browser.
Click your profile icon → Settings.
Navigate to the Connectors section in the sidebar.
Click Add custom connector.
Note: You can add multiple Lemonado connectors if you want to separate different data environments (for example, “Sales Data” and “Marketing Data”).

Step 2 — Add the Lemonado MCP Connector
In the Add Custom Connector dialog, enter the following details:
(These are also available in your Lemonado workspace under AI Connectors)
Name:
LemonadoRemote MCP Server URL:
https://mcp.lemonado.io/mcpAuthentication: Select OAuth (optional)
Click Add to save the connector.
Then click Connect to start authentication.
A browser window will open, prompting you to log in to your Lemonado account and approve access to your chosen AI Connector.
Once authentication completes, your Lemonado connector will show as “Connected” in Claude.


Step 3 — Test Your Connection
Start a new chat in Claude.
Click the Search and tools icon in the message box.
Find Lemonado from the list of available connectors and toggle on.
Try a simple query, such as:
If successful, Claude will return data directly from your connected Lemonado workspace.

Next Steps: Start Querying Your Data
Once connected, Claude can use Lemonado as a read-only data layer for natural-language analysis. Try prompts such as:
“Show this week’s revenue compared to last month.”
“Which Google Ads campaigns drove the most Stripe subscriptions?”
“Find HubSpot contacts who haven’t been reached in the last 30 days.”
All queries run through Lemonado’s unified SQL engine, allowing you to combine and analyze data from multiple sources in one request — securely and in real time.
Best Practices
Keep each connector scoped to the specific data it needs.
Review Lemonado’s audit logs regularly to monitor data access.
Rotate or revoke OAuth tokens periodically for security.
You’ve now connected Claude to Lemonado MCP, enabling secure, real-time access to your business data through natural language.
Lemonado ensures every connection remains read-only, audited, and secure, so you can explore insights confidently without ever exposing or modifying your underlying data.
Share this post

Lane Goedhart
Stop fighting with data. Start feeding your AI.
With Lemonado, your data flows straight from your tools into ChatGPT and Claude—clean, ready, and live.


