Skip to main content

Documentation Index

Fetch the complete documentation index at: https://lava.so/docs/llms.txt

Use this file to discover all available pages before exploring further.

The Lava MCP gives your AI chat tool access to a catalog of connected services — search, communication, productivity, finance, research, AI inference, and more — with auth and billing handled automatically. This quickstart walks you from zero to a successful ask in under 5 minutes. By the end, you’ll have Lava installed in your chat, one service connected, and one ask returning real data.

​
Step 1: Install Lava in Your AI Chat

The fastest path is a one-click install in Claude.ai. Open the link below and approve the connector when prompted. 
https://claude.ai/settings/connectors?modal=add-custom-connector&connectorName=Lava&connectorUrl=https://www.lava.so/mcp
Claude.ai opens its connector dialog, displays “Lava” as the connector name and https://www.lava.so/mcp as the URL, and asks you to confirm. Approve it. Expected result. Lava appears in your Claude.ai connectors list. The first time you use it, Claude.ai prompts you to sign in (covered in Step 2). For Claude Code or Claude Desktop, use the snippets below.

​
Claude Code

claude mcp add --transport http lava https://www.lava.so/mcp

​
Claude Desktop

Add to claude_desktop_config.json: 
{
  "mcpServers": {
    "lava": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://www.lava.so/mcp"]
    }
  }
}

​
Step 2: Sign In to Lava

The first time your chat client uses a Lava tool, Lava redirects you to a browser to sign in. Complete the sign-in flow and return to your chat. Expected result. Your chat client confirms the connection. Lava is now ready to handle tool calls on your behalf.

​
Step 3: Connect Your First Service

Connect web search. In your chat, type: 
Connect Serper to Lava.
The chat calls Lava’s connect_service tool with "serper". Lava returns an authorization URL. 
{
  "url": "https://www.lava.so/auth/connect/serper?session=...",
  "expires_in": 600
}
Open the URL. Lava walks you through whichever auth flow Serper requires (an API-key entry page or an OAuth handoff, depending on the service). Complete the flow and return to your chat. Expected result. Asking the chat to list your connected services now includes Serper: 
What services do I have connected?

{
  "data": [
    { "service": "serper", "connected_at": "2026-04-29T15:00:00Z" }
  ]
}

​
Step 4: Run Your First Ask

Now ask Lava to use the connected service. Type: 
Ask Lava to search the web for the latest Mastra documentation and summarize the top three results.
Lava routes the request through ask, which calls Serper, retrieves results, and synthesizes a summary. Expected result. Your chat returns a paragraph or two summarizing recent Mastra documentation, sourced from Serper’s web search. If you see an insufficient_balance error, continue to Step 5.

​
Step 5: Add Funds to Unlock Paid Providers

Free providers work without funds. Most paid providers require a wallet balance. To add funds, open the dashboard: 
https://www.lava.so/dashboard/wallet
Or ask your chat: 
Add $25 to my Lava wallet.
Lava returns either a list of saved payment methods (if you have one) or a browser checkout URL. Follow the flow to add funds. Expected result. Ask Lava: what's my balance? returns the new total. For deeper coverage, see How to Fund Your Lava Account.

​
What You’ve Done

You installed Lava in your AI chat, signed in, connected a service, and ran your first ask. Your chat can now reach any service in Lava’s catalog through the same set of tools.

​
Next Steps