A read-only MCP server for retrieving and analysing Google Ads account data through Google's query language, including campaign and conversion reports.

Use it to query campaigns, search terms, Performance Max and AI Max data, conversions, change history, and available Google Ads API v24 fields.

It gives an agent a controlled way to inspect advertising data while keeping account changes disabled by default and recording access in an audit log.

quantum-ads — Skill for Claude Code and Codex by Casius999

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Casius999/quantum-ads-mcp --skill quantum-ads

Clone the repo

git clone --depth 1 https://github.com/Casius999/quantum-ads-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/casius999/quantum-ads-mcp/quantum-ads/github.svg)](https://agentmods.dev/skills/casius999/quantum-ads-mcp/quantum-ads)

Your own site

<a href="https://agentmods.dev/skills/casius999/quantum-ads-mcp/quantum-ads"><img src="https://agentmods.dev/badge/skills/casius999/quantum-ads-mcp/quantum-ads/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/casius999/quantum-ads-mcp/quantum-ads"><img src="https://agentmods.dev/badge/skills/casius999/quantum-ads-mcp/quantum-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,550 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00151	$0.02550
Opus 5.5	$0.00060	$0.01020
Sonnet 5.5	$0.00030	$0.00510
Haiku 4.5	$0.00015	$0.00255

Measured 5d ago against content hash 5730f96856d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quantum-ads scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/quantum-ads/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quantum ADS — Google marketing agency control plane (MCP, November 2026)

A FastMCP 4 server (MCP Python SDK 2, protocol revision 2026-07-28) exposing the Google marketing stack as MCP tools on one shared core. Launch: quantum-ads-mcp (stdio) or quantum-ads-mcp serve --transport http (Streamable HTTP behind OAuth 2.1, multi-tenant).

Architecture in one screen

Core (shared): credential store (tokens never reach the LLM), version manager (default Ads API v26, official sunset table, unknown-enum tolerance), GAQL build/validate/run engine with quota governors, safety spine (read-only by default, validate_only preview → two-step confirm token → Ed25519-signed, hash-chained, persistent audit ledger), connector registry + meta-tool discovery.
21 connectors, each reading its API through a named backend (ctx.backend("<key>")). The entrypoint builds every backend the environment can serve (quantum_ads/backends.py); backends are lazy — nothing authenticates until a tool is first called, so one connector's bad credentials never take the server down. An unwired backend answers {error: BACKEND_NOT_CONFIGURED} instead of raising.

When to use

Report on / operate Google Ads (GAQL, opinionated reports, change history, guarded status/budget edits).
Pull GA4 / Search Console / YouTube / BigQuery / Looker data; manage GTM, Merchant Center, Business Profile, DV360/CM360/SA360; upload first-party data via Data Manager.
Generate creative with Vertex AI (Gemini text, Gemini image, Veo video) or run Meridian MMM.
Generate short videos for free with video.generate (Wan 2.2 → LTX-Video on Hugging Face ZeroGPU; daily GPU quota, QUOTA_EXHAUSTED when spent) — prefer it over paid Veo.
Check what changed between Ads API versions (ads.api.version_delta) and how close the pinned version is to sunset (health).

Critical first facts (November 2026)

Google Ads API v26 is current (released 2026-10-14; sunset 2027-11). Supported: v23 (sunset 2027-02), v24 (2027-05), v25 (2027-08). Library google-ads 35. Releases are monthly-cadenced; re-check the sunset table before pinning.
Three Google Ads planes: Google Ads API (campaigns, GAQL reporting) + Data Manager API (Customer Match / offline + enhanced conversions — no longer uploadable via the Ads API) + Merchant API (Shopping catalog — the Content API for Shopping is sunset).
Vertex defaults are GA models: gemini-3.8-flash (text), gemini-3.1-flash-image (image), veo-3.1-generate-001 (video, long-running — poll with vertex.veo.status).
Details: references/google-ads-2026-sota.md.

Read the full file on GitHub · 136 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago Changed · +51 lines 5730f96856d8
6d ago Changed · +20 lines · +63 tokens per session bb0b2e51a039
2mo ago First seen · 65 lines · 88 tokens per session scan A 4e63a657db98

Subscribe to this mod's changes

quantum-ads is a skill published in the GitHub repository Casius999/quantum-ads-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 151 tokens to every session and 2,550 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metrics Marketing and SEO fastmcp google-ads google-ads-api marketing-automation mcp model-context-protocol

quantum-ads next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
quantum-adsCasius999/quantum-ads-mcp	Skill	0	5d ago	MIT	A	151	Claude Code, Codex
fastmcp-client-cliPrefectHQ/fastmcp	Skill	28k	today	Apache-2.0	A	46	Claude Code, Codex
fastmcp-serverPrefectHQ/fastmcp	Skill	28k	today	Apache-2.0	A	27	Claude Code, Codex
code-reviewPrefectHQ/fastmcp	Skill	28k	today	Apache-2.0	A	13	Claude Code, Codex
triaging-incidentsjschuller/mcp-server-servicenow	Skill	27	3d ago	MIT	A	89	Claude Code
reviewing-update-setsjschuller/mcp-server-servicenow	Skill	27	3d ago	MIT	A	82	Claude Code
assessing-change-impactjschuller/mcp-server-servicenow	Skill	27	3d ago	MIT	A	105	Claude Code