ds@mcpanalytics.aiEmail your data and your question and get an answer about your own data, with the method shown.Email your data and question. Get an answer.
Install

Connected in two minutes.
Every client, every option.

npx for Claude Desktop and Cursor, the connector directory for ChatGPT, direct key or OAuth2 for everything else, with troubleshooting for each path.

Pick your client ↓ Get an API key →

Prerequisite: a free account at account.mcpanalytics.ai

# claude_desktop_config.json { "mcpServers": { "mcpanalytics": { "command": "npx", "args": ["-y", "@mcp-analytics/mcp-analytics"], "env": { "MCP_ANALYTICS_API_KEY": "mcp_…" } } } } # restart the client: the tools appear
Setup

Three steps to your first analysis

1

Get your API key

Sign up at account.mcpanalytics.ai, go to account settings, and click Reveal API Key. Copy the key. It starts with mcp_.

You get 30 days of full access when you finish onboarding: every analysis depth, subject to fair use. No credit card required.

2

Pick a connection method

Choose the option that fits your setup. All three connect to the same platform with the same tools.

Option A: npx install

Recommended

One-line install. Works everywhere. The npm package proxies to our API, no local dependencies beyond Node.js.

// ~/.claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcpanalytics": {
      "command": "npx",
      "args": ["-y", "@mcp-analytics/mcp-analytics"],
      "env": {
        "MCP_ANALYTICS_API_KEY": "mcp_your_key_here"
      }
    }
  }
}
// .cursor/mcp.json (or Settings > MCP Servers)

{
  "mcpServers": {
    "mcpanalytics": {
      "command": "npx",
      "args": ["-y", "@mcp-analytics/mcp-analytics"],
      "env": {
        "MCP_ANALYTICS_API_KEY": "mcp_your_key_here"
      }
    }
  }
}
# Add via Claude Code CLI

claude mcp add mcpanalytics \
  -- npx -y @mcp-analytics/mcp-analytics

# Then set your API key in the environment:
# MCP_ANALYTICS_API_KEY=mcp_your_key_here

Option B: Direct API key

No npm needed. Your MCP client connects directly to our API via HTTP. Requires a client that supports custom headers on Streamable HTTP transport.

// Claude Desktop config

{
  "mcpServers": {
    "mcpanalytics": {
      "type": "http",
      "url": "https://api.mcpanalytics.ai/mcp/api-key",
      "headers": {
        "X-API-Key": "mcp_your_key_here"
      }
    }
  }
}

Option C: OAuth2 (experimental)

Experimental. A browser window should open for login on first connection, but this path is not yet reliable across clients. If it does not complete, use Option A or B with an API key.

// Claude Desktop config

{
  "mcpServers": {
    "mcpanalytics": {
      "type": "http",
      "url": "https://api.mcpanalytics.ai/auth0"
    }
  }
}

Browse tools first (no account needed)

Explore the full tool catalog before signing up. Public discovery endpoint, no authentication required. See every analysis available.

# Browse the tool catalog
curl -s https://api.mcpanalytics.ai/.well-known/mcp.json | jq '.tools'

# Or via MCP protocol (for MCP clients)
POST https://api.mcpanalytics.ai/mcp/discover
{"jsonrpc":"2.0","method":"tools/list","id":1,"params":{}}
3

Restart and analyze

Restart your MCP client. MCP Analytics is now available as a tool. Try one of these to get started:

Try saying:

  • "Upload sales.csv and find which products drive the most revenue"
  • "What statistical test should I use for this survey data?"
  • "Run customer segmentation on my Shopify export"
  • "Forecast next quarter's revenue from this time series"
Resources

Go deeper

GitHub

Source code, server.json for MCP Registry, and stdio proxy package.

Developer Docs

REST API, tool discovery, dataset management, and programmatic access.

Full Documentation

All tools, data formats, connectors, pricing, and detailed guides.

Ready to start?

Free account. 30 days of full access. No credit card.

Create free account Star on GitHub ★
WHERE NEXT
referenceRead the docs →Tools, tiers, datasets, and citations, the full reference. data inConnectors →Query GA4 and Search Console directly from chat. for agentsThe agent experience →What your AI assistant can do once it's connected.

Where to start

One email with your data and your question. We take it from there.

MCP Analytics

Data science by email

Send us your data and your question, and we will reply.

ds@mcpanalytics.aimcpanalytics.ai

Try it on your own data

30 days free.

Answers, analytics and custom analytics. No card, no call, nothing to install.

30 days free. →
mcpanalytics.ai

Send us my data →