How to Query Google Ads with Claude / Cursor via MCP (Google Ads MCP Server Setup)

See everything Query Streams can do beyond this guide Get Started Free

Supports

+more

Live Data

Replace exports with on-demand SQL

Excel Sheets

BI & AI Analytics

Ask Nova, get SQL + charts

Meet Nova

Database REST API

One key per partner. No credentials shared.

Build an API

+more

Automation

Scheduled sync to 6+ platforms

Explore

+more

API to SQL

Query APIs with SQL, no code

Explore

+more

AI Database MCP

Claude, Cursor, ChatGPT & Grok talk to your data

Connect AI

Query Streams is a secure, real-time data integration platform that brings every database and SaaS API in your account into Claude, Cursor, ChatGPT, and Grok — through a single MCP key with no firewall changes. This guide walks through the google ads mcp path specifically, so your AI tool can answer plain-English questions about campaigns, ad groups, search terms, and conversions without you exporting reports out of the Google Ads UI or building yet another GAQL query in the Ads Editor. The Network Agent pulls Ads API data into a local DuckDB cache, so the LLM sees clean SQL surfaces (campaigns, keywords, search terms, conversions) instead of raw REST and GAQL. Learn more at QueryStreams.com and sign up for free to start asking your AI tool real Google Ads questions.

What the Query Streams Google Ads MCP server gives you

Other “Google Ads MCP” servers on the open-source landscape connect the AI tool directly to the Ads API and push raw GAQL at it. That works, but it pushes a Google OAuth token into your AI client’s config, leaves the LLM staring at REST resources and field selectors instead of SQL, scopes the AI tool to only Google Ads, and gives you no audit trail of what the AI actually asked. The Query Streams google ads mcp server solves a wider problem: one key, every connector, full audit trail, the agent normalises Ads data into SQL surfaces, and the AI tool never holds your Google credentials.

How it works without opening firewall ports

The Query Streams Network Agent installs once on any host with internet access (the Ads API is reachable from anywhere) and dials one outbound TLS link to the cloud — it calls the Google Ads API with GAQL under the hood, caches the response in a local DuckDB so the AI sees clean SQL surfaces (google_ads_performance, keywords, search_terms, conversions, audiences) instead of REST envelopes, and the AI tool never sees your Google OAuth token, customer ID, or developer token. how the outbound-only connection works →

The MCP key you give Cursor or Claude is scoped (read / analyze / execute), revocable at any time, and rate-limited per-key. The AI tool calls these MCP tools to do its work:

Why Schema Intelligence makes Query Streams MCP different

Most “MCP for Google Ads” servers in the open-source landscape hand your AI tool the same GAQL field reference Google publishes for developers — or worse, the raw information_schema of whatever cache they keep. Field names. Data types. Maybe a primary key. The LLM is left to guess that cost_micros needs to be divided by 1,000,000, that campaign_status is an enum of ENABLED / PAUSED / REMOVED, or that segments_date is the right partition column for “last 30 days.” That’s why the first SQL most LLMs write against a bare Ads schema is wrong — not because the LLM is bad, but because it doesn’t have the data it needs to be right (and an off-by-1,000,000 in cost is the kind of mistake that becomes a slack message).

Query Streams MCP returns that same cached Ads schema enriched with what we call Schema Intelligence (SI) — AI-curated metadata that’s generated by running profiling queries against your actual Google Ads data before the AI client ever asks. When SI is enabled on the Google Ads connector, every schema tool the AI calls (qs_get_connector_schema, qs_get_table_schema, qs_profile_table, qs_get_relationships) returns the bare cached schema plus six layers of curated knowledge. The LLM stops guessing.

To make this concrete, here is what the AI client gets back from a single qs_get_table_schema call against the Google Ads connector’s google_ads_performance table — the denormalized campaign + ad-group + date view that drives 90% of reporting questions — first without Schema Intelligence, then with it.

The six layers Schema Intelligence adds

Each layer addresses a specific class of question the LLM would otherwise have to guess at. SI is opt-in per (connector, database) pair and runs as a one-time profiling pass against your data — it does not change your schema, does not write to your database, and refreshes incrementally when your schema changes.

Same prompt, different SQL

The proof is in the SQL the AI tool actually writes. Same Cursor session, same Claude model, same prompt — “Which campaigns spent the most in the last 30 days, with conversion rate, only enabled campaigns?” Without Schema Intelligence the LLM has to guess. With it, the LLM knows the cost is in micros, the status enum needs filtering, and a NULLIF guard is needed.

MCP not for you? Try Nova AI instead.

Skip the JSON config entirely: Nova AI is built into the Query Streams web portal and asks the same plain-English Google Ads questions (“which keywords are wasting budget this month?”) across every connector you’ve added — same agent, same read-only enforcement, same Schema Intelligence, no MCP plumbing.

Meet Nova AI

Prerequisites

Before you start, make sure you have:

1. A free Query Streams account at my.querystreams.com.
2. The Query Streams Network Agent installed on a machine with internet access — see Download the Query Streams Agent. The Google Ads API is reachable from anywhere, so the agent doesn’t need to live on a specific network.
3. A Google Ads connector configured against the agent — see the existing API Connector Setup guides for OAuth pairing (single account or MCC manager). The agent holds the Google OAuth token, your customer ID, and your developer token; the AI tool never touches any of them.
4. Any MCP-capable AI client. We’ll show Cursor, Claude Desktop, ChatGPT, and Grok in this guide; if you use Windsurf, Zed, Continue, Cline, VS Code Copilot, Codex, or Goose, the config block is essentially the same.
5. Five minutes.

Step 1: Generate an MCP key in Query Streams

Sign in to Query Streams and open the MCP page (or sign in first at my.querystreams.com and click MCP in the left navigation). Click Generate key, give the key a recognizable name (something like cursor-laptop or claude-desktop), and pick the scopes you want this key to have:

• read — the AI can browse connectors and read schema. Required for everything else.
• analyze — the AI can profile tables and discover relationships (sample values, distributions, semantic types). Optional but strongly recommended for paid-search work, where understanding the shape of your campaign data and metric semantics (cost in micros, status enums) matters.
• execute — the AI can actually run SQL. Without this, the AI is read-only against schema metadata only.

For a typical “let Claude analyse my Google Ads data” workflow, all three scopes are appropriate. For a key you’re handing to a teammate or a less-trusted client, drop execute and let them browse only. You can revoke any key at any time from the same page; the AI client will see MCP_KEY_REVOKED on its next call and stop working immediately. There’s no propagation delay.

Copy the key now — Query Streams shows it once, then stores only a hash. If you lose it, generate a new one. The key looks like qsmcp_ followed by 48 random characters and is what your AI client sends in the X-MCP-Key request header.

Step 2: Add Query Streams MCP to your AI client

The configuration is the same shape across every MCP-capable client — an MCP server entry pointing at https://mcp.querystreams.com with your key in the X-MCP-Key header. Pick your client below.

Cursor ~/.cursor/mcp.json

// Edit ~/.cursor/mcp.json
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

Claude Desktop claude_desktop_config.json

// Settings → Developer → Edit Config
{
  "mcpServers": {
    "querystreams": {
      "url": "https://mcp.querystreams.com",
      "headers": {
        "X-MCP-Key": "qsmcp_PASTE_KEY_HERE"
      }
    }
  }
}

ChatGPT Apps & Connectors

// Settings → Apps & Connectors → Add MCP
Server URL  https://mcp.querystreams.com
Auth header X-MCP-Key
Header value qsmcp_PASTE_KEY_HERE

// Requires a paid ChatGPT plan
// (Plus / Pro / Team / Enterprise).

Grok Remote MCP Tools

// Grok → Settings → Tools
{
  "mcp_servers": [{
    "name": "querystreams",
    "url": "https://mcp.querystreams.com",
    "auth_header": "X-MCP-Key",
    "auth_value": "qsmcp_..."
  }]
}

Restart your AI client. On its next start it will discover the eight Query Streams MCP tools listed above and surface them in its tool palette. In Cursor and Claude Desktop you can verify by typing “list connectors” — the AI should call qs_list_connectors and return your Google Ads connector (or each child account if you paired an MCC) along with anything else you have configured.

Step 3: Ask the AI a Google Ads question

You don’t write SQL — the AI does. You ask a question, the AI picks the right MCP tool, the agent runs the query against your cached Google Ads data, and the answer comes back as text plus tables. Three example prompts to try first:

The first time the AI calls a tool, your client may pop up a confirmation prompt asking you to approve the tool call — that’s MCP’s standard consent flow, not anything Query Streams adds. Approve once and the AI proceeds with the rest of the conversation freely. You can revisit the consent at any time in your client’s settings.

Frequently asked questions

Get started

Related guides: Download the Query Streams Agent | API Connector Setup | All MCP Server guides | Nova AI text-to-SQL

Category: MCP Server

Tags: mcp, claude, cursor, google-ads, paid-search, ppc, marketing-analytics, api-connector

Meta Description: Query Google Ads with Claude or Cursor via MCP. Cached SQL surfaces, MCC support, no firewall holes. Free.