adops-mcp
AdOps MCP is a CSV-first ad analytics and optimization server for Google Ads and Meta Ads — no OAuth or API keys required. Import CSV exports or seed demo data, then use your AI assistant to:
Import & Setup: Import Google/Meta Ads CSV exports (
ad_csv_import), seed a demo portfolio of 8 campaigns/30 days of data (ad_demo_seed), or register platform connections manually (platform_connect)Campaign Management: List, create, update, and batch pause/resume up to 50 campaigns across platforms
Performance Reporting: Generate unified cross-platform reports with totals, top performers, and underperformers (
ads_report); get demographic, geo, and device audience breakdowns (audience_insights); look up platform-specific creative specs (creative_specs)Budget Optimization: Analyze allocation with AI-driven recommendations (
budget_analyze), transfer budget between campaigns across platforms (budget_reallocate), and export recommendations as Google Ads Editor CSV, Meta Ads Manager CSV, JSON, or Markdown (ads_export_recommendations)Advanced Analytics: Detect CPC spikes, CTR drops, spend surges, and conversion cliffs (
anomaly_detect); run A/B tests with statistical significance scoring (ab_test_analyze); benchmark against 9 industry verticals (competitor_benchmark); forecast spend, conversions, and ROAS for 7/14/30 days (forecast_spend)
Provides unified campaign management for Facebook Ads (as part of Meta Ads), including listing campaigns, creating/updating campaigns, generating performance reports, and accessing Facebook Ads API data through platform connections.
Provides unified campaign management for Google Ads, including listing campaigns, creating/updating campaigns, generating performance reports, budget analysis, and accessing Google Ads API data through platform connections.
Provides unified campaign management for Meta Ads (Facebook Ads), including listing campaigns, creating/updating campaigns, generating performance reports, budget analysis, and accessing Meta Ads API data through platform connections.
AdOps MCP
CSV-first analytics & optimization for Google Ads + Meta Ads — inside Claude, Cursor, and any MCP client.
Export a CSV from Google Ads or Meta Ads Manager → import into AdOps → ask your AI assistant anything about your campaigns.
No OAuth. No developer tokens. No API approval queues. Your data stays on your machine.
Why CSV-first?
Google Ads API and Meta Marketing API are powerful but gated: developer token approval takes days, Meta app review takes weeks, OAuth flows are fragile. For most advertisers those barriers never clear.
AdOps takes a different path. Every ad platform's dashboard already has a Download / Export button that produces a CSV of exactly what you care about: campaign performance, day-segmented metrics, spend, conversions, ROAS. AdOps reads that CSV and runs the same analysis you'd get from a $200/mo optimization suite — anomaly detection, budget allocation, A/B significance, forecasting, industry benchmarks — directly inside your AI assistant.
You stay in control of your data. You don't hand credentials to a third party. You don't wait 3 weeks for a review.
Related MCP server: google-ads-mcp
Features
17 MCP tools covering the full ad analytics lifecycle
4 MCP resources for at-a-glance dashboards
CSV import from Google Ads Editor, Google Ads web UI, and Meta Ads Manager — with automatic format detection (US vs European number formatting, CRLF vs LF, BOM handling)
Unified cross-platform schema — Google and Meta campaigns normalized into a single
UnifiedCampaign/UnifiedMetricsmodelAI-powered recommendations — budget reallocation, scaling high-ROAS campaigns, pausing zero-conversion ones
Bulk-edit CSV export — turn recommendations into Google Ads Editor / Meta Ads Manager CSVs you can paste straight into the dashboard for one-click bulk updates
Statistical anomaly detection — CPC spikes, CTR drops, spend surges, sensitivity-configurable
A/B test analysis with confidence scoring
9-vertical industry benchmarks built-in (eCommerce, SaaS, B2B, etc.)
Spend & conversion forecasting (7/14/30 days)
Demo mode — seed a realistic portfolio to try the tools before importing your own data
91 automated tests — TypeScript strict mode, Zod validation throughout
Quick Start
npm i adops-mcp-serverAdd to your MCP client (Claude Desktop claude_desktop_config.json, Cursor, VS Code, Windsurf):
{
"mcpServers": {
"adops": {
"command": "node",
"args": ["path/to/node_modules/adops-mcp-server/dist/index.js"]
}
}
}Restart your client. Then, inside Claude:
> Seed demo data so I can explore AdOps(calls ad_demo_seed)
Or import your real data:
> Import ~/Downloads/google-ads-report.csv as a Google Ads CSV(calls ad_csv_import with platform=google, csv_path=...)
Exporting CSV from Your Ad Dashboard
Google Ads
Open ads.google.com → Campaigns view
(Optional) Click Segment → Day in the toolbar for daily metrics
Click Download (⬇) icon → choose .csv format
Save to disk, give the absolute path to
ad_csv_import
Meta Ads Manager
Open business.facebook.com → Ads Manager
Switch to Campaigns tab (not Ad Sets or Ads — campaign-level rollups)
(Optional) Breakdown → Time → Day for daily metrics
Click Reports → Export → Campaign performance (.csv)
Save to disk, give the absolute path to
ad_csv_import
Both exports work out-of-the-box with or without day segmentation. Without a Day column, you get one aggregated metric row per campaign. With Day segmentation, you get daily time-series data — which powers forecasting and anomaly detection properly.
Tools
Tool | Description |
| Seed a realistic cross-platform demo portfolio (8 campaigns, 30 days of metrics) to try AdOps before importing real data |
| Import a Google Ads or Meta Ads CSV export — every other tool operates on this data |
| Export budget_analyze recommendations as Google Ads Editor CSV, Meta Ads Manager CSV, JSON, or Markdown — one bulk-paste and your ad dashboard reflects the AI's plan |
| Register a data source connection manually (alternative to CSV import, for scripted workflows) |
| List and filter campaigns across all imported platforms |
| Add a campaign manually (useful for what-if planning) |
| Update campaign settings in local storage (budget, status, bidding, schedule) |
| Batch pause or resume up to 50 campaigns |
| Generate unified cross-platform performance report |
| Analyze budget allocation, produce scaling/pausing recommendations |
| Transfer budget between campaigns across platforms |
| Demographic / geographic / device breakdowns |
| Platform-specific image, video, and text requirements reference |
| Detect performance anomalies with configurable sensitivity |
| Compare two campaigns with statistical significance testing |
| Compare your metrics against industry averages (9 verticals) |
| Forecast spend, conversions, ROAS for the next 7/14/30 days |
Resources
Resource | Description |
| Cross-platform dashboard summary |
| All active campaigns with key metrics |
| Budget allocation across platforms |
| Recent performance anomalies and warnings |
Unified Metrics Schema
AdOps normalizes metrics across platforms:
Metric | Formula | Notes |
CTR | clicks / impressions × 100 | Click-through rate (%) |
CPC | spend / clicks | Cost per click |
CPM | spend / impressions × 1000 | Cost per 1000 impressions |
ROAS | conversion_value / spend | Return on ad spend |
CPA | spend / conversions | Cost per acquisition |
Conversion Rate | conversions / clicks × 100 | % |
CSV column mapping:
AdOps Field | Google Ads CSV | Meta Ads CSV |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| — |
|
|
| — (Google-only) |
European locale numbers (125,50 = 125.50) and semicolon-delimited CSVs are auto-detected.
Configuration
AdOps is stateless from the network's point of view — no API keys, no OAuth. The only configuration is where it persists imported data:
Variable | Description | Default |
| Directory for JSON persistence |
|
All other behavior is controlled via tool arguments.
Pricing
Tier | Price | Features |
Free | $0 | 1 imported CSV per day, demo mode, all 17 tools read-only |
Pro | €24 lifetime | Unlimited imports, full CRUD, all analytics tools |
Agency | $59/mo | Multi-account, white-label reports, priority support |
Available via GitHub (self-hosted, free) or the MCPize marketplace (managed).
Development
git clone https://github.com/enzoemir1/adops-mcp.git
cd adops-mcp
npm ci
npm run build
npm test # 91 tests across 10 suites
npm run inspect # Open MCP InspectorTests
91 tests covering:
CSV parser (11 tests): RFC 4180 quoting, BOM, European/US number formats, delimiter detection
Google Ads CSV import (7 tests): campaigns report, day segmentation, objective mapping, European locale
Meta Ads CSV import (5 tests): Meta-specific columns, currency detection from header, objective mapping, reach/frequency capture
Export recommendations (8 tests): Google Ads Editor CSV format, Meta Ads Manager CSV format, JSON wrapper, Markdown rendering, min_delta_pct filter, limit, by_type summary
Storage: Connection CRUD, campaign search, metrics aggregation, batch inserts
Analytics: Metric calculations, performance reports, forecasting, benchmarks
Optimizer: Budget analysis, reallocation, scaling/pausing recommendations
Anomaly: CPC spike detection, conversion drops, sensitivity, severity sorting
E2E Workflow: 14 real user scenarios
Roadmap
v1.3 — Add Google Ads Editor
.csv.gzand Excel.xlsxsupportv1.4 — Live Google Ads / Meta Ads API integration as an optional enterprise feature (BYOK — bring your own developer token + app review)
v2.0 — Multi-user server mode with JWT auth for team deployments
Pro License
AdOps ships in Free mode — ad_demo_seed, ad_csv_import, platform_connect, campaign_list, campaign_create, campaign_update, campaign_pause_resume, ads_report, budget_reallocate, audience_insights, and creative_specs are open. The following tools require a Pro license:
ads_export_recommendations— bulk-edit CSV export for Google Ads Editor / Meta Ads Managerbudget_analyze— AI budget allocation analysis with action recommendationsanomaly_detect— statistical anomaly detectionab_test_analyze— A/B test z-test with significance + upliftforecast_spend— 7/14/30-day spend & ROAS forecastcompetitor_benchmark— industry benchmark comparison
Buy a Pro License (€24, lifetime, 3 machines): https://automatiabcn.lemonsqueezy.com/buy/1525c929-832c-4472-a88a-58edbfa4e87b
Or get the Indie MCP Stack Bundle (€69, all 4 servers).
export LEMONSQUEEZY_LICENSE_KEY=YOUR-KEY-HEREOr in your MCP client config:
{
"mcpServers": {
"adops-mcp": {
"command": "npx",
"args": ["-y", "adops-mcp-server"],
"env": { "LEMONSQUEEZY_LICENSE_KEY": "YOUR-KEY-HERE" }
}
}
}Validation is cached locally for 24 h — fully offline-capable after first run.
License
MIT License. See LICENSE for details.
Built by Automatia BCN.
Available Tools
17 toolsab_test_analyzeA/B Test AnalysisARead-onlyIdempotent
Compare two campaigns as A/B test variants and determine statistical significance. Input: campaign_id_a, campaign_id_b, primary_metric ("ctr"|"conversion_rate"|"roas"|"cpc"|"cpa"). Runs a two-proportion z-test (or means comparison for continuous metrics), computes p-value and 95% confidence interval, identifies the winner, and returns {winner, confidence_level, p_value, lift_percent, sample_size_a, sample_size_b, significant (bool), recommendation}. Use with lift ≥5% and p<0.05 as a decision rule.
Inputs: campaign_id_a (required), campaign_id_b (required), primary_metric.
ad_csv_importImport Ad Campaign Data from CSVA
Import real campaign + performance data from a Google Ads or Meta Ads CSV export. After import, every AdOps tool (ads_report, budget_analyze, anomaly_detect, ab_test_analyze, competitor_benchmark, forecast_spend) operates on your real data. No API keys or OAuth required — just export from your ad dashboard and import here.
HOW TO EXPORT: • Google Ads: Reports → Campaign performance → Download → Comma-separated (.csv). Include "Day" segment for daily metrics. • Meta Ads Manager: Campaigns view → Export → Campaign performance (.csv). Check "Include breakdowns: By day" for daily metrics.
INPUT: Provide either csv_path (absolute path to file on disk) OR csv_content (raw CSV string). Optional connection_name groups imports; re-importing with the same name appends new data. Returns a summary with campaigns_imported, metrics_imported, warnings, and the connection id to reference in other tools.
Inputs: platform (required), csv_path, csv_content, connection_name, +1 more.
ad_demo_seedSeed Demo Ad PortfolioA
Create a realistic cross-platform ad portfolio for trying AdOps without real data. Seeds 2 connections (Google + Meta), 8 campaigns across performance tiers, 30 days of daily metrics (240 rows), and pre-computed anomaly alerts. Use this to explore what AdOps can do, then switch to ad_csv_import with your real Google/Meta exports for production use. Safe to call multiple times — appends a new portfolio each call.
Inputs: no named parameters.
ads_export_recommendationsExport Budget Recommendations (Bulk-Edit Ready)ARead-onlyIdempotent
Export budget_analyze recommendations as a Google Ads Editor CSV, Meta Ads Manager CSV, JSON, or Markdown — so you can take action in one bulk paste instead of editing campaigns one by one. AdOps does not call Google/Meta write APIs (that would require OAuth + developer token approval for every user); instead, this tool hands you the exact CSV rows those dashboards expect, and you paste them in. Perfect for the "pause anything with CPA over 50 and reallocate budget" workflow. Use platform=google with format=google_ads_csv (import into Google Ads Editor). Use platform=meta with format=meta_ads_csv (bulk edit in Meta Ads Manager Power Editor). Use json to pipe into n8n or your own automation. Use markdown for human review before acting. min_delta_pct filters out noise (e.g. 0.15 = only show changes >=15%).
Inputs: format (required), output_path, optimization_goal, platform, +2 more.
ads_reportCross-Platform Performance ReportARead-onlyIdempotent
Aggregate performance metrics across Google Ads and Meta Ads into a single unified view. Input: date_range ({start, end} as YYYY-MM-DD, defaults to the last 7 days), optional platform filter, optional campaign_ids filter, optional sort_by ("spend"|"roas"|"conversions"|"ctr"|"cpc"), and limit. Returns {period, totals (spend, impressions, clicks, conversions, revenue, ROAS, CPC, CTR), by_platform, campaigns[] (sorted per sort_by), top_performers, underperformers}. This is the entry point for most analysis workflows.
Inputs: platform, date_range, campaign_ids, sort_by, +1 more.
anomaly_detectDetect Performance AnomaliesARead-onlyIdempotent
Scan campaigns for statistical anomalies vs. a rolling baseline. Flags CPC spikes, CTR drops, sudden spend surges, and conversion cliffs. Input: sensitivity ("low"|"medium"|"high" — controls the z-score threshold), lookback_days (baseline window, default 14), optional platform filter. Returns {anomalies_found, severity_breakdown (critical|high|medium|low counts), alerts[] (each with campaign_id, metric, baseline, current, deviation, severity, reason)}. Run daily to catch issues before they burn budget.
Inputs: platform, sensitivity, lookback_days.
audience_insightsAudience InsightsARead-onlyIdempotent
Demographic and behavioural breakdown of the audiences served by your ads. Input: platform (optional — omit for all platforms) and optional campaign_id to scope to a single campaign. Returns {age_distribution, gender_distribution, top_geos, top_interests, device_breakdown, total_impressions, engagement_rate}. Use when refining targeting or reporting audience coverage.
Inputs: platform (required), campaign_id.
budget_analyzeBudget Analysis & OptimizationARead-onlyIdempotent
Analyze how the current ad budget is distributed and produce actionable reallocation recommendations. Input: optimization_goal ("maximize_roas"|"maximize_conversions"|"minimize_cpa") and optional platform filter. Returns {goal, current_allocation (by platform + campaign), recommendations[] (each with campaign_id, current_budget, suggested_budget, rationale, expected_impact), projected_lift}. Pair with budget_reallocate to execute the recommendations.
Inputs: platform, optimization_goal.
budget_reallocateReallocate BudgetA
Transfer a dollar amount from one campaign's daily budget to another. Works across platforms (e.g. shift $50/day from a Google Ads search campaign to a Meta Ads retargeting campaign). Input: from_campaign_id, to_campaign_id (UUIDs, must differ), amount (positive number in campaign currency). Rejects the call if from_campaign_id === to_campaign_id or if the source campaign would go below zero. Returns the updated budgets for both campaigns.
Inputs: from_campaign_id (required), to_campaign_id (required), amount (required).
campaign_createCreate CampaignAIdempotent
Create a new ad campaign in the AdOps workspace. Accepts unified parameters (platform, name, objective, bidding_strategy, daily_budget, currency, start_date, end_date, targeting) and stores a canonical UnifiedCampaign record with status="draft". Returns the created campaign summary plus next_steps guidance. Requires an active platform connection (see platform_connect) — will auto-associate the first active connection for the chosen platform.
Inputs: platform (required), name (required), objective (required), daily_budget (required), +5 more.
campaign_listList CampaignsARead-onlyIdempotent
Unified listing of campaigns across Google Ads and Meta Ads in a single view. Optional filters: platform ("google_ads"|"meta_ads"), status ("draft"|"active"|"paused"|"ended"|"archived"), query (free-text over campaign name). Pagination via limit (default 20, max 100) and offset. Returns {total, showing, offset, campaigns[]} where each campaign summary includes id, name, platform, status, objective, daily_budget, currency, and start_date. Use the returned id with campaign_update, campaign_pause_resume, or ab_test_analyze.
Inputs: platform, status, query, limit, +1 more.
campaign_pause_resumePause or Resume CampaignsAIdempotent
Batch-change the status of up to 50 campaigns in one call. action="pause" sets status to "paused"; action="resume" sets status to "active". Missing campaign_ids are reported in the errors array but do not fail the whole batch. Returns {action, updated, failed, campaigns[], errors?}. Use this for emergency pause during an incident or weekend shutoff.
Inputs: campaign_ids (required), action (required).
campaign_updateUpdate CampaignAIdempotent
Patch-update an existing campaign. Pass campaign_id (UUID from campaign_list or campaign_create) plus any subset of: name, status, daily_budget, bidding_strategy, end_date. Fields you omit are left unchanged. Returns {message, updated_fields[], campaign} or an error if campaign_id is not found. Prefer campaign_pause_resume for batch status changes.
Inputs: campaign_id (required), name, daily_budget, total_budget, +3 more.
competitor_benchmarkIndustry Benchmark ComparisonARead-onlyIdempotent
Compare your ad performance against industry averages for a chosen vertical. Input: industry (e.g. "ecommerce", "saas", "finance", "healthcare", "education", "travel", "real_estate", "legal"), optional platform filter. Returns {industry, your_metrics, benchmarks (CTR, CPC, CPM, conversion_rate, CPA, ROAS industry averages), comparison (percent above/below benchmark per metric), recommendations[]}. Benchmarks are curated static tables — not live market data.
Inputs: industry (required), platform.
creative_specsCreative SpecificationsARead-onlyIdempotent
Platform-specific creative requirements for ad formats. Returns the exact image dimensions, aspect ratios, video duration and codec, headline/primary-text character limits, supported CTA buttons, and file size ceilings for each ad format. Input: platform ("google_ads"|"meta_ads") and optional format filter (e.g. "responsive_display", "video", "carousel", "single_image"). Use this before building creatives to avoid rejection at upload time.
Inputs: platform (required), format.
forecast_spendSpend & Performance ForecastARead-onlyIdempotent
Project future ad spend and performance based on recent historical trends. Input: period_days ("7"|"14"|"30") and optional platform filter. Uses moving-average extrapolation of spend, impressions, clicks, conversions, and revenue across the last 14 days. Returns {period_days, platform, projected (spend, impressions, clicks, conversions, revenue, ROAS, CPC, CTR), confidence_level, warnings[]}. Confidence drops when recent data is volatile or campaigns were paused.
Inputs: period_days, platform.
platform_connectConnect Ad PlatformAIdempotent
Register a Google Ads or Meta Ads account in the AdOps workspace so subsequent tools (campaign_list, campaign_create, ads_report) can target it. Input: platform ("google_ads"|"meta_ads"), name (display label), account_id (the external ad account id). Returns the stored connection object with a generated UUID and status="active". Safe to call with the same platform+account_id — returns the existing connection instead of erroring (idempotent).
Inputs: platform (required), name (required), account_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 17 tools
Most tools map to clearly distinct workflows—reporting, budget analysis/execution, A/B testing, forecasting, anomaly detection—and the descriptions reinforce those boundaries. The main residual ambiguity is between campaign_update and campaign_pause_resume, both of which can change status, though their batch vs. single-campaign roles are reasonably clear.
Names are readable and often follow an object-first style like campaign_create, budget_analyze, and anomaly_detect. However, the pattern is inconsistent: campaign_list and ads_report are noun phrases, forecast_spend reverses the order, and ad_csv_import / ad_demo_seed mix objects, formats, and verbs in unpredictable ways.
Seventeen tools is slightly above the ideal 3–15 range, but the broad ad-ops scope justifies the count: ingestion, setup, campaign management, reporting, analysis, forecasting, and exportable recommendations all earn their place. It feels comprehensive rather than bloated.
The tool surface covers data import, account registration, campaign lifecycle management, reporting, budget analysis and execution, forecasting, anomaly detection, A/B testing, benchmarking, and exportable recommendations—so core workflows have no dead ends. Missing pieces like single-campaign detail retrieval, account disconnection, and ad-group-level management are minor relative to the stated campaign-level purpose.
Maintenance
Related MCP Connectors
Meta Ads MCP server: run Facebook and Instagram campaigns, ad sets, ads and reports from AI.
Google Ads MCP server: run Search, Display, Demand Gen and PMax campaigns from AI.
Google Ads MCP server — manage campaigns, keywords, and metrics.
Meta Ads and Google Ads MCP server: 250+ tools for Claude, ChatGPT, Cursor and Codex.
Related MCP Servers
AlicenseNot gradedqualityFmaintenanceMCP server for managing Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads via AI. 210+ tools including account audits, wasted spend detection, and PMax insights.2MIT- AlicenseAqualityDmaintenanceMCP server for Google Ads API — 22 tools for campaigns, keywords, RSAs, assets, audiences, geo/device performance, impression share, auction insights, and budget pacing. Community edition with B2B/agency-focused tooling beyond the official Google MCP.221MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for managing ad campaigns across Google Ads, Meta, and more. Enables deploying campaigns, checking performance, and managing budgets from terminal or AI assistants.MIT
- FlicenseNot gradedqualityDmaintenanceA comprehensive MCP server for managing and analyzing Meta Ads (Facebook/Instagram) with over 80 natural-language tools for AI agents like Claude Desktop.-