Adops MCP server

Read from the package source without running it. The installed server may list more.

• ab_test_analyze

  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

• ad_csv_import
• ad_demo_seedwrite action

  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 por

• ads_export_recommendations
• ads_report

  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, c

• anomaly_detect

  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, m

• audience_insights

  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.

• budget_analyze

  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

• budget_reallocatewrite action

  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. Retu

• campaign_createwrite action

  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 fir

• campaign_list

  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

• campaign_pause_resume

  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.

• campaign_updatewrite action

  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.

• competitor_benchmark

  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[]}.

• creative_specs

  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 c

• forecast_spend

  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[]}. Conf

• platform_connect

  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

• Code scan50 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 14 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Adops: common questions

Is Adops MCP server safe?

Yes, by our scan: it is graded A (94/100). Read the Adops safety report

How do I install Adops?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Adops need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Adops maintained?

The last commit was 15 days ago (2026-09-13). The latest release is v1.3.0.

What can I use instead of Adops?

Servers from other publishers that do the same job: NotFair-MetaAds MCP server and Netdata MCP server.