Srednoff Google Ads MCP Account Auditor

Google Ads MCP Account Auditor

Structure a read-only Google Ads account review with reporting contracts and actionable evidence gaps.

Manager/customer scope confusion, invalid GAQL field combinations, segmented-cost duplication, immature conversions, and mixed conversion actions can make a polished account audit materially wrong.

Who This Is For

An agency analyst or in-house acquisition lead using an authorized Google Ads reporting connector and needing defensible account diagnostics rather than unreviewed optimization actions.

What You Get

• A standalone, domain-specific agent workflow with decision rules and stop conditions.
• Evidence requirements, structured report guidance and missing-data handling.
• Synthetic worked examples and supporting reference material.
• Optional offline evidence-precheck source where the licensed delivery allows execution; not an automatic artifact scanner.

Expected Deliverables

• connector_contract: provenance, version, observed tool inventory, read allowlist, and limitations
• scope_map: authorized customers, manager relationships, exclusions, and missing hierarchy evidence
• query_ledger: GAQL, metadata basis, grain, scope, extraction time, completeness, and result status
• spend_bridge: micros normalization, spend-only control, segment duplication, and residual
• conversion_quality: actions, counting, inclusion, values, import/consent evidence, and lag
• findings_backlog: classification, evidence, owner economics, confidence, no-change decisions, and separately approved next actions

How The Workflow Proceeds

1. Freeze the account allowlist and verify the supplied customer-manager mapping. Accessible-customer discovery is not assumed to enumerate every client under every manager; request a scoped hierarchy export where required.
2. Inspect the connector's actual tool inventory and version. Build a read-only allowlist; a tool name or MCP annotation alone is not a security guarantee, and a write-capable fork is not treated as the official reporting server.
3. Use current resource metadata to design GAQL selections with compatible fields and segments. Record resource grain and query purpose; do not guess version-specific fields or claim unexecuted queries succeeded.
4. Normalize cost_micros with exact arithmetic and reconcile campaign totals to a spend-only control query. Avoid adding cost across conversion-action rows or incompatible segment grains.

The remaining workflow covers validation, failure recovery and an evidence-linked handoff.

Bring These Inputs

• Owner-approved customer IDs, manager/customer relationships, prohibited accounts, and redacted connector tool/capability inventory.
• Customer, campaign, budget, and conversion-action metadata exports with API/connector version and extraction timestamps.
• GAQL query text, resource/field metadata, result exports, pagination/truncation status, and an unsegmented spend control total.
• Timezone, currency, cost_micros normalization, VAT/tax treatment, attribution model, interaction/conversion date basis, and conversion-lag policy.
• Owner economics and outcome definitions: primary/secondary actions, counting method, values, imports, qualified leads, orders, paid sales, and refunds.

Scope And Compatibility

This is a workflow toolkit used by your connected AI agent, not a hosted service, installed API client, autonomous executor or security/compliance certification. You supply the model, authorized tools and project evidence. It does not provide access to advertising, analytics, billing or production accounts. No business outcome or token saving is guaranteed.

Agensi delivery is agent-only. Do not save or export the proprietary source. If local helper execution is unavailable, the agent follows the review workflow and marks the helper NOT_EXECUTED; no local-script execution is promised for this channel.

Validation Transparency

Packaged offline supplied-evidence checks: PASS. Retained synthetic text-response cases: 8/8; scope PASS_SCOPED. These tests are not real-client task trials or marketplace-runtime certification.

Commercial Use And Support

Use project-specific outputs in personal, business and client work under the included Commercial License 1.0. Historical MIT and third-party rights remain unchanged; mandatory marketplace terms prevail. No proprietary source redistribution is included. Publisher: Ivan Srednoff / Srednoff.Agency.

FAQ

Will it make changes automatically? No. Analysis does not authorize spending, publication, deployment or account mutations.

Are examples client results? No. Examples are explicitly synthetic DEMO DATA.

Does it require Srednoff OS? No. The workflow is standalone; external tools and subscriptions are not included.

Is the launch price a proven optimum? No. It is a scoped introductory price informed by comparable offers, not sales forecasts or fake discounts.