Right Side UpRight Side Up × Xnurta
Webinar resources · Nov 18, 2026

Here's how we're taking Amazon Ads management to the next level with Xnurta's MCP.

This page shows how Right Side Up's marketplace team uses the Xnurta MCP with Claude to catch problems sooner, act across thousands of campaigns, and prove results to clients. This page pairs examples from across the RSU team with a deeper case study on a lab-supply brand that sells largely to businesses. It covers how we think about the Xnurta MCP, when we reach for the Xnurta MCP, and the proof.

875We asked the Xnurta MCP for data 875 times on one client account from Oct 30 to Nov 8.
28,492That profile holds 28,492 campaigns, and one question can cover all of them.
3–4 minWeekly campaign upkeep now takes 3–4 minutes instead of several hours.
−16.5 ptsWeekend ACOS fell from 33.5% to 17.0% after a dayparting schedule made from Xnurta MCP data.
5.79×October's estimated incremental ROAS was about 45% above the client's 4.00× iROAS goal.

Figures are as of Nov 8, 2026. Sources and windows are under Sources and method.

The Xnurta MCP can read the entire ad account and make bulk changes once a person approves the change.

The Xnurta MCP works alongside Xnurta AI and the console. Claude + Xnurta MCP adds a layer that can read the whole account, combine account data with other data, and make bulk changes once someone approves them. We give each layer the job it does best.

People
People own strategy, targets and approvals.

We set margin-based targets, decide what to test, approve every change, and explain results to the client.

Claude + Xnurta MCP
Claude reads the whole account and makes bulk changes through the Xnurta MCP.

Claude answers questions across tens of thousands of campaigns and combines the answers with Seller Central, margin or test data. Claude drafts and previews bulk edits, then confirms each one landed.

Insight Agent
Insight Agent gives quick answers inside Xnurta.

Insight Agent handles fast questions and canned reports inside Xnurta, with no setup.

Xnurta AI
Xnurta AI optimizes around the clock.

AI Managed Groups adjust bids, budgets and placements against each group's target, all day, every day.

Every Claude + Xnurta MCP task follows the same three steps.

Claude + Xnurta MCP does the reading and drafting. A person approves anything that spends money. Then Claude pulls the live settings through the Xnurta MCP to confirm the change landed, and Xnurta's Operation Logs record the change.

Ask

Claude + Xnurta MCP answers questions that used to mean a stack of exports and a pivot table. Nothing in the account changes.

  • The Xnurta MCP reports performance by day, hour, placement, search term or audience.
  • The Xnurta MCP shows current settings, group targets and stock levels.
  • The Xnurta MCP shows who changed what and when, whether a person, a rule, Xnurta AI or Claude.
Ad performanceCampaign settingsOperation LogsAMC audience results
Act

Claude + Xnurta MCP drafts the changes and shows you the old and new values. Claude makes the changes only after you confirm.

  • The Xnurta MCP changes bids, budgets, negatives and pauses across many campaigns at once.
  • The Xnurta MCP edits AI Managed Groups and their schedules, and creates new campaigns.
  • Any change that affects spend needs a one-time confirmation token.
Bulk editsAI Managed Group schedulesAI Managed Groups
Reset

Claude + Xnurta MCP confirms each change landed. Once attribution settles, Claude reviews the results and rolls back changes that didn't pay off.

  • Claude pulls the live settings through the Xnurta MCP after every change to confirm the change landed.
  • Claude re-pulls results after attribution settles, about 7 days for SP and 14 for SB and SD.
  • Claude also undoes temporary changes on schedule, such as restoring pre-promo bids after peak.
Operation LogsPromo resetScheduled re-checks
House ruleEvery connection starts read-only. Claude + Xnurta MCP proposes each change, a named person approves the change, and Claude then confirms the change landed. Claude + Xnurta MCP does the legwork, and the expert owns the call.

Reach for the Xnurta MCP when the job is big, repeated, or spans more than one data source.

Our rule of thumb: use the Xnurta MCP when the job is big, repeated, needs data from more than one place, or needs a careful bulk change. Anything Xnurta AI already handles, or that only the console can do, stays there.

Which tool fits which job
JobXnurta AIInsight AgentClaude + Xnurta MCPXnurta console
Hold bids and budgets to target, all day, every day●–○○
A quick question about one profile○●○○
Questions across thousands of campaigns, combined with Seller Central, margin or test data–○●–
Bulk changes across hundreds of campaigns, previewed first––●○
Weekly tasks Claude can learn once and repeat––●–
Add or edit schedules on existing AI Managed Groups––●●
Create schedule and dayparting templates, Rule-mode settings and word lists–––●
Run AMC analyses and create audiences–––●
Explain results to a client, with charts and checked numbers–○●○

● best fit ○ can do – not available. Template, Rule-mode and word-list limits come from the Xnurta MCP's own documentation and Xnurta, Nov 9, 2026. Xnurta expects AMC audience creation in the Xnurta MCP by the end of the year. The Xnurta MCP can already read AMC audience performance.

Do these things.

  1. Start with read-only. Every client gets a read-only connection before anyone makes a change.
  2. Confirm every change landed. After each change, pull the live settings and compare them with what you approved. Xnurta's copy of your settings can trail Amazon by 20+ minutes, so a mismatch right after a change usually means Xnurta is still syncing.
  3. Wait for attribution. One day's SP attributed sales rose 4.1% between pulls a day apart.
  4. Keep attributed, marginal and incremental ROAS apart. Clients ask "did it pay?", and only the last one answers that.
  5. Get the full list. On large accounts, results can be cut off at a row limit, so check that you got everything before drawing conclusions.

Avoid these mistakes.

  1. Don't hand-edit campaigns in AI Managed Groups. Change the group's target, action space or schedule instead.
  2. Don't stack bid adjustments blind. Placement and audience bid adjustments multiply. A 25% Top of search bid adjustment on top of a 150% audience bid adjustment produced a $24.44 CPC on a $96.90 deposit-bag product from a lab-supply brand.
  3. Don't mix up what a metric covers. ASIN-level ad totals cover SP and SD only. ASIN "Sessions" in Xnurta are counted differently from Seller Central sessions.
  4. Don't read "missing" as zero. An empty result can mean the data wasn't returned, so confirm before reporting zero.

These six strengths helped win the RSU team over to Xnurta's MCP.

The Xnurta MCP makes the whole account readable in one sitting, so the team spends its time on decisions. Each strength comes with an example from our accounts.

One question can cover the whole account.

There's no sampling and no exporting. One question reads every campaign, search term and Xnurta AI change.

The lab-supply account has 28,492 campaigns and 36,569 search terms.

Hours of work turn into minutes.

Once Claude learns a weekly task, each run through the Xnurta MCP is quick. The person still reviews each run.

An apparel brand's weekly top-100 upkeep went from several hours to 3–4 minutes.

The Xnurta MCP finds settings that collide.

Some problems live between two settings, and neither screen shows them on its own.

An automated rule and bid dayparting fought over the same bids, and placement and audience bid adjustments stacked into a $24.44 CPC.

The Xnurta MCP runs hygiene audits nobody has time for.

These checks are easy to get wrong and slow to do by hand.

Negatives were blocking wanted search terms, including some carried over when campaigns were copied.

Claude + Xnurta MCP works on questions while the call is still going.

A question from a client or partner call goes straight to Claude, which starts the analysis right away.

On our Nov 9 call with Xnurta, we started an audit of stacked bid adjustments and an audience-test design check live.

Bulk changes come with guardrails.

Claude + Xnurta MCP drafts hundreds of rows with the spend behind each. You preview and confirm the rows, and Claude then checks that each one landed.

One change sheet held 176 negatives and 206 pauses, and schedules on 227 campaigns were checked cell by cell after saving.

These numbers show how much ground the Xnurta MCP covers.

36,569One Insight Agent answer covered 36,569 search terms.
56,503We grouped 56,503 Xnurta AI changes from 14 days by action type.
1,499We reviewed 1,499 AI Managed Groups covering 6,091 campaigns.
330We found 330 ASINs selling with no ad support, worth 3.0% of revenue.
875We asked the Xnurta MCP for data 875 times across 11 conversations with Claude on one account in 10 days.
85 daysOne request pulled 85 days of daily account data for this page.
2,141The Operation Logs traced 2,141 audience changes.
12 in ~32 hWe started 12 projects at once on Nov 6 and delivered them by Nov 7. Nine drew on live Xnurta data.

The RSU team learned to trust the Xnurta MCP one step at a time.

Everyone on the team started with read-only access. Each person climbs the same four steps at their own pace, and the setup makes the safe path the default.

  1. 1

    Start with read-only.

    Connect every client with a read-only MCP token and ask anything; the token can only read.

    This is where everyone starts.
  2. 2

    Let Claude + Xnurta MCP analyze.

    Claude finds the issue and drafts the fix. The specialist makes the change in the console.

    Part of the RSU team works this way: Claude + Xnurta MCP analyzes, and the specialist applies the edits.
  3. 3

    Preview the changes and suggestions.

    Claude + Xnurta MCP makes the change after the specialist approves a preview, then Claude confirms the change landed.

    On a fitness nutrition brand, the RSU team checked every change at first, and the edits have been accurate.
  4. 4

    Teach Claude a recurring task.

    Walk Claude through a weekly job once, such as updating a top-100 top-of-search campaign. After that, Claude runs that job through the Xnurta MCP on request, asks when something is unclear, and waits for a go-ahead.

    The RSU team taught Claude an apparel brand's weekly top-100 upkeep. The teaching took a while, and each run now takes minutes.

This is how we connect clients.

One folder per client holds that client's Read & Write MCP token. A separate "All Clients" folder holds a read-only MCP token for every account, so questions across clients stay read-only. Xnurta built a setup Skill for this after our team asked for it in early November.

The Xnurta MCP turned hourly data into a dayparting schedule that cut weekend ACOS in half.

This case covers a lab-supply brand with a large Amazon Business channel. Right Side Up took over advertising on Sep 15, 2026, running it through Xnurta. The account is too large to review campaign by campaign, which is where the Xnurta MCP earns its keep.

28,492The US profile has 28,492 campaigns, and 4,110 of them are active.
6,091Xnurta AI manages 6,091 campaigns in 1,499 AI Managed Groups.
2.86×Contribution break-even ROAS is 2.86×, and the client's iROAS goal is 4.00×.
9,358We classified 9,358 ASINs for Featured Offer work.

B2B revenue grew faster than total revenue in every period.

Each bar shows revenue change against the same dates in 2025.

Source: Seller Central ordered product sales (B2B and B2C split), as verified in the October 2026 client report. Percentages only; dollar figures are client-confidential.

Data table
5.79×

We proved the spend paid. We grew ad spend 34% year over year from Sep 15 to Oct 31. An incrementality analysis on daily data pulled through the Xnurta MCP puts October's incremental ROAS at 5.79× (80% range 3.99–7.86×). The client's target is 4.00×. Contribution break-even is 2.86×.

The iROAS figure comes from a statistical analysis, so it is an estimate. Attributed ROAS is reported separately.

Here is October in one table.

Measure, Oct 1–31, 2026vs Oct 2025
Total revenue+11.4%
B2B revenue+14.3%
Revenue vs client plan+1.2%
TACOS8.25% vs 6.99%

Growth reflects pricing, the B2B program and advertising together, and the account was already growing before Sep 15. The Xnurta MCP's part is speed, coverage and proof.

This chart shows daily ad spend, with weekend and AI-managed spend marked.

Spend indexed to 100 = average daily spend, Aug 15 – Sep 14. Every bar comes from one live Xnurta MCP request made for this page.

Source: Xnurta ad performance data through the Xnurta MCP (get_ads_perf), client US profile, campaign level by day, Aug 15 – Nov 7, 2026, pulled Nov 8. Sales for Nov 1–7 are still settling. Xnurta's AI Dashboard puts AI-managed campaigns at 73% of spend and 84% of ad sales for Nov 2–8. Those campaigns were picked for AI Managed Groups, so the split reflects that selection as well as AI management.

Data table

Dayparting cut weekend ACOS in half

The chart compares ACOS before and after the Oct 16 dayparting schedule, with the change in average spend per day under each pair.

Before: Sep 19 – Oct 11 (4 weekends). After: Oct 17–25 (2 weekends, attribution settled). Same live pull. Weekend ad sales per day fell 45% while weekend spend per day fell 72%.

Data table

Each card below is one win from this account.

Each card says what Claude + Xnurta MCP did, what we found, and how far the work went. The tag on each card shows its status: executed and checked live, live check, analysis, or proposed and waiting on a client decision.

Executed · checked liveAd performance · hourly

Hourly data became a dayparting schedule on 227 campaigns.

Did
Claude + Xnurta MCP mapped ACOS by hour from 28 days of data and turned it into hourly bid adjustments for Xnurta's bid dayparting template. After saving, Claude checked every hour against the plan.
Found
Weekends ran near 34% ACOS against 19% on weekdays once budgets ran flat all week.
33.5% → 17.0%This is weekend ACOS before and after, from a live pull.
Live checkOperation LogsCampaign settings

Claude + Xnurta MCP answered "Did my new campaigns go live?" in minutes.

Did
One question checked newly launched campaigns against the live campaign settings and the Operation Logs.
Found
The new 36-campaign AI Managed Group was live. Older campaigns on the same 9 products were still running, so the two would bid against each other.
2 sets of campaigns, 9 productsWe caught the overlap before the two sets kept bidding against each other.
AnalysisAd performance · ASIN

Claude + Xnurta MCP set up an incrementality test to measure what the ads caused.

Did
Claude + Xnurta MCP tracked each ASIN day by day, matched it to the campaigns advertising it, and compared advertised ASINs with similar ones before and after. The pass/fail rule was written down before any results came in.
Found
Two standard sanity checks passed, so the test can be trusted.
483 ASINsEach one is tracked day by day and matched to the campaigns that advertise it.
AnalysisAMC audience resultsOperation Logs

Claude + Xnurta MCP compared AMC audiences with their own campaigns.

Did
Claude + Xnurta MCP compared every AMC and Amazon audience with the rest of the same campaigns, on the same days. The Operation Logs showed an audience swap on Oct 28 that a performance report alone would have hidden.
Found
Past buyers returned 11.7× attributed ROAS against 8.8× for the rest of their campaigns. Seven custom audiences got zero impressions.
2,141 changesThese audience-type changes on 2,093 campaigns were traced to the day.
ProposedInsight AgentAd performance · placement

Claude turned 17 Insight Agent reports into one action plan.

Did
Claude read every Xnurta Insight Agent report on the account and merged them into one prioritized plan.
Found
Top of Search gets 39% of placement spend but brings 53% of sales at 14.4% ACOS. 61% of spend sits in 1,434 campaigns running at 35.5% ACOS.
3,919 termsThese converting search terms haven't been harvested into their own targets yet.
AnalysisAd performance · ASINFeatured Offer (Buy Box) %

Claude + Xnurta MCP traced why 25 products slowed down, across ads, sales and the Featured Offer.

Did
Claude + Xnurta MCP ranked every child ASIN by year-over-year decline, reconciled to the account total, and diagnosed each top decliner with ad, sales and Featured Offer (Buy Box) data.
Found
Lower B2B bulk orders drove 29% of the top-25 decline; reduced ad support drove 16%. The account still grew.
6 causesEach cause across the top 25 has an owner and a next step.
ProposedAd performanceCampaign settings

Claude + Xnurta MCP drafted approval-ready change sheets that respect AI Managed Groups.

Did
Claude + Xnurta MCP drafted negatives, pauses, consolidations and bid rows with the spend behind each. Campaigns inside AI Managed Groups were flagged for a target change. Converting terms were protected from negation.
Found
98 of the 120 bid rows sat inside AI Managed Groups, so they became target-change requests for those groups.
176 negatives · 206 pausesEach row shows its spend and is waiting on client approval.
AnalysisAd performanceCampaign settings

Claude + Xnurta MCP tested the obvious fix first.

Did
Claude + Xnurta MCP tested the obvious fix, re-enabling 81 paused ASINs, against the data before acting. Claude held 8 bid changes at the preview step.
Found
The paused ASINs ran at 41.6% ACOS. The real issue was dayparting lifting a very low base bid into junk clicks: CPC fell 89% and CVR fell from 11.7% to 1.1%.
Waste avoidedWe skipped a re-launch that would have added spend at 41.6% ACOS.
Live · checked every monthAd performanceAMC audience results

Our monthly client report checks its own numbers before it ships.

Did
The monthly client report combines Xnurta and Seller Central data, and every figure in the text is recalculated separately before it ships.
Found
Attributed sales change after the fact: one day's SP sales moved +4.1% between two pulls a day apart. Pull results after attribution windows close.
651 of 651All 651 figures matched a separate recalculation on the latest version.
ProposedCampaign settingsAd performance

B2B ad tests only touch profitable products.

Did
Claude + Xnurta MCP checked every ASIN for margin, performance and stock before it could enter a test-versus-control split.
Found
Amazon Business-exclusive campaigns ran at 12.4% ACOS, against 19.8% for the whole account (Insight Agent).
3,682 → 80We checked 3,682 ASINs, and 80 passed every check.
AnalysisInsight AgentOperation Logs + budgets

Insight Agent found efficient campaigns starved of budget.

Did
We asked Xnurta's Insight Agent which campaigns ran out of budget in the past 7 days while holding ACOS at 15% or lower. Insight Agent combined out-of-budget events, serving status and spend against budget.
Found
Insight Agent found 466 out-of-budget events on 202 campaigns from Oct 16 to 22. Of those campaigns, 31 were capping out at 1.2% to 14.6% ACOS on very small daily budgets.
31 campaignsThese low-ACOS campaigns were losing hours to budget caps. The count is a minimum, since one day's Operation Logs were too large to read in full.
Live checkCustom dashboard

A weekly alert board turns 28,492 campaigns into a short list.

Did
We set up an "Ad Alert" dashboard from Xnurta templates with five rules: spend with no orders, and spend at ACOS above 50%, for campaigns and search terms.
Found
For Nov 2–8, the board listed 5 campaigns over $50 with no orders, 24 campaigns over $20 above 50% ACOS, 10 search terms over $20 with no orders, and 27 search terms over $20 above 50% ACOS.
5 · 24 · 10 · 27These are the rows to review per rule for Nov 2–8. Attribution is still settling, so ACOS may fall.

Xnurta MCP wins from the RSU team.

Our ecommerce team shared these examples in Slack and at our Nov 9 team meeting. We asked for one or two examples each. These are their own accounts of the work, lightly edited. People and client names are left out; brands are described by category.

These three wins are in the webinar.

$24.44

Stacked bid adjustments turned one click into a quarter of the product’s price.

A 25% Top of search bid adjustment on top of a 150% audience bid adjustment multiplied to about 3.1 times the base bid. That produced a $24.44 CPC on a $96.90 product. Claude + Xnurta MCP found the stacking by checking both settings together, and we lowered the audience bid adjustment.

RSU team · lab-supply brand
1,000+

One pass paused 1,000+ discontinued items in nearly 1,000 campaigns.

A client discontinued more than 1,000 items. Claude + Xnurta MCP paused them in every campaign they were live in, in under 20 minutes, including a preview before anything changed.

RSU team
3–4 min

An apparel brand’s weekly top-100 upkeep went from several hours to 3–4 minutes.

We taught Claude the job once. Each week Claude decides what stays and what goes in the brand’s top-of-search campaign, confirms with the account lead, then makes the change through the Xnurta MCP.

RSU team · apparel brand

Here are ten more wins from the team.

We catch problems before they cost money.

We caught an automated rule and bid dayparting running on the same campaigns at the same time, working against each other.

RSU team

We flagged an unusual spike in Off-Amazon clicks on certain campaigns for two clients.

RSU team

We found negatives added by earlier automated rules, or carried over when campaigns were copied, that were blocking terms from serving in an exact-match campaign. We now make these fixes live through the Xnurta MCP.

RSU team · fitness nutrition brand

We run an overnight check across a very large account for anything outside set guardrails: CPCs out of range per target and campaign, unexpected traffic, and CTR or CVR changes.

RSU team

We act across thousands of campaigns.

Claude + Xnurta MCP checks whether new top sellers are in ads yet. On an account with 1,000+ campaigns, 250K items and 250+ new items every week, Claude compares top sellers with campaign coverage, so new winners get into ads quickly.

RSU team

We spend smarter.

We found campaigns running out of budget early and worked out the exact bid cut to keep them live all day. Several then drove higher campaign sales at a lower CPC, because they stayed in auctions all day.

RSU team

We check how often campaigns run out of budget, and on which days.

RSU team

We harvest and negate keywords and product targets from search-term data.

RSU team

We plan ahead and prove results.

For a category with a long attribution window, we made a table that maps ROAS from day 1 to the close of the window, and shows how holiday shipping cutoffs change the curve.

RSU team

We use hourly charts of ACOS and conversion to set dayparting strategy and explain it to clients. Xnurta raised the account's dayparting campaign limit to 6,000 on request.

RSU team · lab-supply brand

Try these 28 questions through the Xnurta MCP. Each one has paid off for our team.

Our team asks these in Claude with the Xnurta MCP connected, on real client accounts. Copy one and swap in your own targets, where you see X, and your own dates. Ask questions only read data. Act questions show a preview and wait for your OK. Black Friday is Nov 27 and Cyber Monday is Nov 30.

AskRun a nightly guardrail sweep.
For every enabled campaign, compare yesterday with the prior 7-day daily average. Flag CPC more than 30% above its own average per target, traffic or CTR swings above 40%, CVR drops above 30%, and any campaign that ran out of budget before 6 pm. Group by severity and show the top 10 with the numbers.
This question only reads data.
AskFind negatives that block wanted terms.
List negative keywords and negative product targets that match or contain search terms converting in other campaigns over the last 60 days, including negatives carried over when campaigns were copied. Show the blocked term, where it converts, and the negative blocking it.
This question only reads data.
AskCatch rules that fight each other.
Check the Operation Logs for the last 14 days. List campaigns where an automated rule and bid dayparting, or a rule and Xnurta AI, changed the same bid or budget within 24 hours. Show who changed what and when.
This question only reads data.
AskAudit stacked bid adjustments.
Across enabled and paused targets and search terms (not archived), find cases where a placement bid adjustment and an audience bid adjustment stack to push ACOS above our 18% limit. Run 14-, 30- and 90-day lookbacks separately and show the bid adjustments behind each case.
This question only reads data.
AskFind efficient campaigns that are starved of budget.
Which campaigns ran out of budget in the past 7 days while holding ACOS at 15% or lower? Use out-of-budget events, serving status and spend against budget. If any result is cut off at a row limit, say so and treat the list as a minimum.
This question only reads data.
AskSee budget cap-outs by hour.
Using hourly campaign data for the last 3 Saturdays and Sundays, which campaigns ran out of budget, at what hour, and what share of daily spend was gone by noon? Only list campaigns with ACOS below our 20% target.
This question only reads data.
AskCheck an audience test design.
I want to A/B test AMC audiences on one campaign using duplicated campaigns, low base bids and equal audience bid adjustments. Push back on anything that would bias the result, such as Amazon favoring the audience with the most past conversions, or placement bid adjustments multiplying with audience bid adjustments.
This question only reads data.
AskCheck that new campaigns went live.
Did the campaigns I launched in the last 3 days go live? Check their current settings and the Operation Logs. Flag any older campaigns still advertising the same products, so the two sets don't bid against each other.
This question only reads data.
AskFind top sellers that aren't in ads yet.
Compare this week's top 100 sellers by units with the ASINs advertised in enabled campaigns. List every top seller with no active ad, with its units and sales, and the existing campaign it fits best.
This question only reads data.
AskFind products selling with no ad support.
Which ASINs had sales last month but no ad spend? Show units, sales and each one's share of total revenue, sorted by sales.
This question only reads data.
AskMap ACOS by hour for dayparting.
Using the last 28 days of hourly data for enabled SP campaigns, build a day-of-week by hour table of ACOS and conversion rate. Mark the hours above our X% ACOS target and suggest a bid adjustment for each hour. Don't change anything.
This question only reads data.
AskFind the bid cut that keeps a campaign live all day.
For campaigns that ran out of budget before 6 pm on 3 or more of the last 7 days, estimate the bid cut that would keep each one serving until midnight at its current budget. Show the usual out-of-budget time, current CPC and suggested CPC.
This question only reads data.
AskSee which days campaigns run out of budget.
Count out-of-budget events by campaign and day of week for the last 30 days. Show which campaigns run out most often, on which days, and their ACOS.
This question only reads data.
AskSpot unusual Off-Amazon clicks.
Compare Off-Amazon clicks per campaign for the last 7 days with the prior 28-day daily average. Flag campaigns where they more than doubled, with spend and sales beside each one.
This question only reads data.
AskCompare audiences with the rest of their campaigns.
For every campaign with an AMC or Amazon audience bid adjustment, compare the audience's ROAS and CPC with the rest of the same campaign on the same days over the last 30 days. List audiences with zero impressions, and check the Operation Logs for audience changes in that window.
This question only reads data.
AskSummarize what Xnurta AI changed.
Group every Xnurta AI change from the last 14 days by action type and campaign type. Show the counts, the campaigns with the most changes, and how their spend and ACOS moved.
This question only reads data.
AskCompare placement spend with placement sales.
Break down spend, sales and ACOS by placement (Top of search, Rest of search, Product pages) for the last 30 days. Show where each placement's share of spend differs most from its share of sales.
This question only reads data.
AskExplain why products slowed down.
Rank child ASINs by sales decline over the last 4 weeks against the prior 4 weeks. For the top 25, check ad spend, conversion rate and Featured Offer (Buy Box) percentage, and name the most likely cause for each.
This question only reads data.
AskCheck before you relaunch paused products.
Before we relaunch these paused ASINs, show how each one did in its last 90 days of advertising: spend, sales and ACOS, plus why it was paused if the Operation Logs say. Flag any above our X% ACOS target.
This question only reads data.
ActDraft negatives and preview them first.
From the last 30 days of search terms, find terms with 20+ clicks and no orders that are off-category for this catalog. Draft them as negative exact in their source campaigns. Skip any term on our protected list. Show me the preview and wait for my OK before submitting.
You confirm before anything changes.
ActAdd weekend schedules to managed groups.
For these AI Managed Groups, show each group's current schedules, then draft a weekly Friday-to-Sunday schedule with the settings I give you. Preview every group before saving, then pull the saved schedules and confirm they match.
You confirm before anything changes.
ActKeep the top-100 top-of-search campaign current.
Compare this week's top-100 sellers with the ASINs in our top-of-search campaign. Draft the adds and pauses, ask me about anything unclear, and wait for my OK before changing anything.
You confirm before anything changes.
ActLift budgets for peak.
For Nov 27-30, propose a 30% budget increase on campaigns that capped out before 6 pm on at least 2 of the last 7 days and have ROAS above 4. Exclude campaigns in AI Managed Groups. Preview only.
You confirm before anything changes.
ActLower stacked audience bid adjustments.
For the stacked bid adjustments you found, draft a lower audience bid adjustment so the combined bid stays under the limit I give you. Show old and new values, wait for my OK, then confirm each change landed.
You confirm before anything changes.
ActHarvest search terms that convert.
Find search terms with 2 or more orders in the last 60 days at or below our X% ACOS target that aren't exact-match keywords anywhere. Draft them as exact-match keywords in the right campaigns, and as negative exact in their source campaigns. Show the preview and wait for my OK.
You confirm before anything changes.
ActPause discontinued items everywhere.
Here is a list of discontinued SKUs. Find every campaign and ad group where they're advertised and draft a pause for each ad, with its spend in the last 30 days. Wait for my OK before submitting, then confirm each pause landed.
You confirm before anything changes.
ResetPut everything back after peak.
List every bid, budget and placement change people made between Nov 20 and Dec 1, with the pre-promo value. Wait until Dec 14 so SB and SD attribution has settled, then stage the resets by post-promo performance. Don't apply anything yet.
This one lists changes without applying them.
ResetRe-check the client report.
Re-pull last month's results after attribution has closed (7 days for SP, 14 for SB and SD) and recalculate every figure in our client report. Flag any number that moved more than 1% since the first pull.
This question only reads data.
Now · Nov 18–25

Connect read-only first. Find budget cap-outs by hour and ASINs that will run out of stock before Dec 1. Clean search-term waste before traffic peaks.

Peak · Nov 27–30

Set break-even ROAS from current margin. Claude + Xnurta MCP proposes each change, a person confirms it, and Xnurta's Operation Logs record it.

After · Dec 1 onward

Wait about 7 days for SP and 14 for SB and SD before judging Cyber Monday, then reset with a plan.

Here's why the RSU team loves the Xnurta MCP and what we'd like to see next.

Every ad platform has rough edges. What keeps us on this one is how much ground the Xnurta MCP covers, how well its changes work in practice, and how quickly Xnurta acts on feedback.

After a couple of months on Xnurta, we're more pleased every week, and the Xnurta MCP has been especially nice to work with.
RSU team · on the Xnurta platform
Jobs that used to take several hours now take Claude three or four minutes. We still oversee each run, and Claude asks when something is unclear.
RSU team · on weekly upkeep for an apparel brand
We were nervous at first and checked every change. On that account, the edits have been accurate.
RSU team · on live edits for a fitness nutrition brand

These quotes are paraphrased from our Nov 9, 2026 team meeting and Xnurta call.

Xnurta has already done a lot for us.

  • Xnurta raised our dayparting campaign limit to 6,000 when we asked.
  • Xnurta built a permissions setup Skill for Read only and Read & Write MCP tokens by client, after our team asked in early November.
  • Xnurta made Insight Agent usage limits refresh weekly, and offered more if we run out.
  • Xnurta added budget columns to the campaigns view: current budget, budget status and last out-of-budget time.
  • Xnurta takes feature requests on our weekly call, including the ones listed here.

This is what we'd love next.

  • We'd like control over trigger thresholds for optimizations and recommendations.
  • We'd like to save or star Insight Agent questions. The suggested questions change on each visit, so good ones get lost.
  • We'd like up to 10 audience bids per campaign, as Amazon allows. Xnurta supports one today.
  • We'd like to create schedule templates through the Xnurta MCP. Schedules on existing groups already work, but templates still need the console.
  • We'd like AMC audience creation in the Xnurta MCP, which Xnurta expects by the end of the year.
  • We'd like the Amazon Business placement bid adjustment in the Xnurta MCP's batch update tool, so B2B tests can run entirely through the Xnurta MCP.
  • We'd like a higher row limit on Operation Logs. On Oct 16, one day's SP Operation Logs hit the 10,000-row limit, and campaign budget events were cut off.
  • We'd like prior-year ASIN rows, so year-over-year product work can use Xnurta data alone.
  • We'd like audience sizes for non-Shopify AMC audiences, plus complete results on large pulls.
  • We'd like a "downloaded" marker in the Skill Hub.

Every number on this page comes from the sources below.

Team examples
Right Side Up #ecomm-team Slack thread, Nov 5–6, 2026. Each example is an RSU team member's own report and was not re-measured for this page.
Live ad data
Xnurta ad performance data through the Xnurta MCP (get_ads_perf), client US profile, campaign level by day, Aug 15 – Nov 7, 2026, pulled Nov 8 for this page. Dayparting before/after windows: Sep 19 – Oct 11 vs Oct 17–25.
Revenue
October 2026 client report: Seller Central sales. Periods compare the same calendar dates in 2025. Every report figure matched a separate recalculation (651 of 651).
Incremental ROAS
Incrementality analysis from the October 2026 client report, on Xnurta and Seller Central data through Oct 31. October iROAS median 5.79×, 80% range 3.99–7.86×. Break-even 2.86× = 1.0175 / 35.56% contribution margin before ads.
Insight Agent findings
17 Xnurta Insight Agent reports on the client's US profile, read Nov 6, 2026, plus the Oct 22 budget cap-out chat, read Nov 9. Opportunity sizes there are upper bounds.
Xnurta dashboards
The "AI Dashboard" and "Ad Alert" custom dashboards on the client's US profile, Nov 2–8, 2026, read in the Xnurta web app on Nov 9. Attribution for that week is still open.
Nov 9 calls
Right Side Up's weekly call with Xnurta and our marketplace team meeting, Nov 9, 2026, from Granola transcripts. Team statements are paraphrased.
Xnurta MCP capabilities
The Xnurta MCP's own documentation of what the Xnurta MCP can do, checked Nov 10, 2026: weekly schedules on existing AI Managed Groups can be created, edited and deleted; Rule-mode settings and word lists cannot be changed.
Case-study cards
Working files from Right Side Up's Claude conversations on this client, through Nov 8, 2026. "Executed" means the change was made and then confirmed in the live settings. "Proposed" means it awaits client approval.
Xnurta MCP request count
Xnurta MCP requests logged in 23 Claude Code conversation logs for this client, Oct 30 – Nov 8, 2026. Conversations run elsewhere are not counted.
Not covered
Four other custom dashboards (trend and template boards created Oct 29), the Audit and AI Summary pages, and the Sponsored Brands video chat were not read. No scheduled reports exist on the profile, and no Insight Agent chats were started after Nov 6.