Skip to main content
Glama

AdOps MCP

CSV-first analytics & optimization for Google Ads + Meta Ads — inside Claude, Cursor, and any MCP client.

License: MIT TypeScript MCP

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 / UnifiedMetrics model

  • AI-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-server

Add 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

  1. Open ads.google.com → Campaigns view

  2. (Optional) Click Segment → Day in the toolbar for daily metrics

  3. Click Download (⬇) icon → choose .csv format

  4. Save to disk, give the absolute path to ad_csv_import

Meta Ads Manager

  1. Open business.facebook.com → Ads Manager

  2. Switch to Campaigns tab (not Ad Sets or Ads — campaign-level rollups)

  3. (Optional) Breakdown → Time → Day for daily metrics

  4. Click Reports → Export → Campaign performance (.csv)

  5. 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

ad_demo_seed

Seed a realistic cross-platform demo portfolio (8 campaigns, 30 days of metrics) to try AdOps before importing real data

ad_csv_import

Import a Google Ads or Meta Ads CSV export — every other tool operates on this data

ads_export_recommendations

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

platform_connect

Register a data source connection manually (alternative to CSV import, for scripted workflows)

campaign_list

List and filter campaigns across all imported platforms

campaign_create

Add a campaign manually (useful for what-if planning)

campaign_update

Update campaign settings in local storage (budget, status, bidding, schedule)

campaign_pause_resume

Batch pause or resume up to 50 campaigns

ads_report

Generate unified cross-platform performance report

budget_analyze

Analyze budget allocation, produce scaling/pausing recommendations

budget_reallocate

Transfer budget between campaigns across platforms

audience_insights

Demographic / geographic / device breakdowns

creative_specs

Platform-specific image, video, and text requirements reference

anomaly_detect

Detect performance anomalies with configurable sensitivity

ab_test_analyze

Compare two campaigns with statistical significance testing

competitor_benchmark

Compare your metrics against industry averages (9 verticals)

forecast_spend

Forecast spend, conversions, ROAS for the next 7/14/30 days


Resources

Resource

Description

ads://overview

Cross-platform dashboard summary

ads://campaigns

All active campaigns with key metrics

ads://budget

Budget allocation across platforms

ads://alerts

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

spend

Cost (USD equivalent auto-converted if micros)

Amount spent (USD/EUR/...)

impressions

Impressions

Impressions

clicks

Clicks

Link clicks

conversions

Conversions

Results (Purchases/Leads/etc.)

conversion_value

Conv. value

Purchases conversion value

reach

—

Reach (Meta-only)

quality_score

Quality Score (if present)

— (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

ADOPS_DATA_DIR

Directory for JSON persistence

./data

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 Inspector

Tests

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.gz and Excel .xlsx support

  • v1.4 — 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 Manager

  • budget_analyze — AI budget allocation analysis with action recommendations

  • anomaly_detect — statistical anomaly detection

  • ab_test_analyze — A/B test z-test with significance + uplift

  • forecast_spend — 7/14/30-day spend & ROAS forecast

  • competitor_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-HERE

Or 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 tools
ab_test_analyzeA/B Test AnalysisA
Read-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)A
Read-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 ReportA
Read-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 AnomaliesA
Read-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 InsightsA
Read-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 & OptimizationA
Read-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 CampaignA
Idempotent

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 CampaignsA
Read-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 CampaignsA
Idempotent

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 CampaignA
Idempotent

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 ComparisonA
Read-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 SpecificationsA
Read-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 ForecastA
Read-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 PlatformA
Idempotent

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

    A4/5.0

    Scored across 17 tools

    Disambiguation4/5

    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.

    Naming Consistency3/5

    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.

    Tool Count4/5

    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.

    Completeness4/5

    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

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      F
      maintenance
      MCP 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.
      2
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      MCP 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.
      22
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP 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
    • F
      license
      Not graded
      quality
      D
      maintenance
      A comprehensive MCP server for managing and analyzing Meta Ads (Facebook/Instagram) with over 80 natural-language tools for AI agents like Claude Desktop.
      -