google-ads-analyzer
Provides a local MCP server that connects to the Google Ads API, exposing read tools (GAQL search, list accessible customer IDs) and additional write tools (add negative keywords, pause/enable campaigns, update campaign budgets, change bidding strategies, and pause/enable ad groups/ads) so an LLM/agent can analyze and manage Google Ads accounts.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Uses Google ADC and an Ads developer token (stronger than no auth). The README indicates required OAuth scope for adwords access, implying OAuth-based security. However, the provided content does not mention least-privilege scopes per tool, TLS/verification details for the MCP transport, nor how secrets are handled/logged by the server. Write tools increase operational risk if not protected by agent-level confirmation and access control.
⚡ Reliability
Best When
You want an agent connected to Google Ads that can both retrieve reporting data and perform specific write operations using Google’s official Ads API scopes/credentials.
Avoid When
You cannot tolerate the risk of the model triggering write tools (even if unintended) or you lack guardrails, least-privilege credentials, and monitoring/auditing for changes.
Use Cases
- • Agentic analysis of Google Ads performance via GAQL queries
- • Listing accessible Google Ads customer IDs for an authenticated user
- • Applying operational changes from natural language (e.g., pausing campaigns/ad groups/ads, updating budgets/bidding strategies)
- • Managing negative keywords at scale for campaigns via the assistant
- • Faster iteration cycles where an agent can inspect account data and then execute bounded changes
Not For
- • Unattended, fully-automated budget/strategy changes without human review
- • Accounts or operations requiring a separate approvals workflow/audit trail beyond what the README describes
- • Teams that cannot provide and manage Google Ads API credentials securely
- • Applications needing a hosted public API/SDK instead of a local MCP server
Interface
Authentication
Uses Google Application Default Credentials and requires the Google Ads API scope https://www.googleapis.com/auth/adwords (per README). OAuth complexity is managed by Google ADC; the MCP server setup requires correct environment variables and access permissions for the Ads account(s).
Pricing
No pricing information in the provided README/repo metadata; costs would primarily be your own infrastructure plus Google Ads API usage (and any LLM tooling you connect to).
Agent Metadata
Known Gotchas
- ⚠ Write tools can materially change campaigns/budgets/bidding/keywords; agents must have guardrails/confirmation steps.
- ⚠ Many prompts require a customer ID; multi-customer workflows should ensure the correct customer context.
- ⚠ Negative keyword matching types (BROAD/PHRASE/EXACT) must be set correctly to avoid unintended keyword blocking.
- ⚠ Budget and bidding changes should be validated (currency/target values) before execution.
- ⚠ The README notes an extra header for usage data collection; ensure this is acceptable for your environment and that it does not leak sensitive info.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for google-ads-analyzer.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.