Data Analyst4 MCP serversMCP 2025-06-18 Stable

Data Analyst Loadout

4 MCP servers for ad-hoc analysis without firing up a notebook

Last verified:

Query Postgres or BigQuery in plain English, drop the result into Excel for a chart, and document what you found in Notion. The full ad-hoc analysis loop in one chat.

Install Data Analyst Loadout

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres", "postgresql://readonly@localhost:5432/mydb"]
    },
    "bigquery": {
      "command": "npx",
      "args": ["-y", "bigquery-mcp"],
      "env": { "GOOGLE_APPLICATION_CREDENTIALS": "/Users/you/.gcp/service-account.json" }
    },
    "excel": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-excel"]
    },
    "notion": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-notion"],
      "env": { "NOTION_TOKEN": "secret_..." }
    }
  }
}

After pasting, fully restart your MCP client. Replace placeholders (paths, API keys) with your own values.

What's in this loadout

  • Postgres MCP Server
    coremcp

    Run analytical queries against your operational DB or replica.

  • BigQuery MCP
    coremcp

    Query the warehouse for product analytics, marketing data, and joined tables.

  • Excel MCP
    optionalmcp

    Pivot, chart, and format the results without leaving the chat.

  • Notion MCP Server
    optionalmcp

    Document the analysis, link to the SQL, and share with stakeholders.

What you can do with it

  • Cohort retention deep-dive

    Using bigquery, pull weekly retention curves for users who signed up in March 2026 split by acquisition channel. Drop the table into excel as a heatmap and write a 5-bullet summary in a new notion page under "Weekly Analyses".

  • Compare prod vs warehouse

    Count yesterday's orders in postgres and compare against the same day in bigquery's orders table. Flag any rows where the totals diverge by more than 1%.

  • Quick SQL → chart

    Run this query against postgres: SELECT date_trunc('day', created_at), count(*) FROM orders WHERE created_at > now() - interval '30 days' GROUP BY 1. Drop the result into excel and chart it.

Client compatibility

  • Claude Desktop 0.7.4
    Tested ✓
  • Cursor 0.42+
    Tested ✓
  • Windsurf 1.4
    Tested ✓
  • Continue 0.9
    Untested

Variants

Heavy version

Adds Snowflake for teams on a different warehouse and Tableau for handoff.

Adds: snowflake-mcp, tableau-mcp

Lite version

Just Postgres + Notion. Run queries, document findings.

Removes: bigquery-mcp, mcp-server-excel

FAQ — Data Analyst Loadout

  • What is the Data Analyst Loadout?

    Query Postgres or BigQuery in plain English, drop the result into Excel for a chart, and document what you found in Notion. The full ad-hoc analysis loop in one chat. It includes 4 MCP servers: Postgres MCP Server, BigQuery MCP, Excel MCP, Notion MCP Server.

  • Does this loadout work with Cursor and Windsurf?

    Yes. The config block above is one JSON object that drops into Claude Desktop's, Cursor's, or Windsurf's MCP config. Each client uses the same mcpServers schema; only the file path differs.

  • How long does setup take?

    About 3 minutes the first time: copy the config, paste it into your client's MCP configuration file, replace placeholder API keys with your own, and restart the client.

  • Can I customise this loadout?

    Yes. Use the Lite version if you want fewer servers, or the Heavy version to add 2 more for advanced workflows. You can also remove any individual server by deleting its entry from the JSON.

  • How much does it cost?

    Loadout itself is free. Most listed servers are open-source and free to run. Servers that talk to paid SaaS (Stripe, SendGrid, Linear, etc.) follow that vendor's pricing.

  • When was this loadout last verified?

    Last verified on 2026-04-24. We re-test featured loadouts at least monthly and update the config when MCP servers ship breaking changes.