Data & use cases from AppsFlyer’s MCP, Agent Hub, and AI Assistant
53% of accounts using MCP return on day 7 or later
39% deployed ‘Weekly Performance Report’ – the most popular agent
20% of AI assistant questions analyzes or retrieves data
Trusted signal layer is the key to AI impact
AI is only as good as the data that feeds it. After all, agents are just obedient optimizers: they pursue the objective you give them using the data signals you provide them. If those signals are fragmented, duplicated, self-reported, or poorly governed, automation does not reduce the problem — it accelerates it.
The marketers getting the most from AI are therefore not only the ones with access to the most sophisticated models, but also the ones who have solved the signal problem first, and operate based on data that they trust.
AppsFlyer sits at the center of that trusted signal layer for thousands of marketing teams. MCP gives those teams programmatic access to this layer where they can query all their attribution and performance data through any interface. The Agent Hub deploys always-on agents that monitor, alert, and surface opportunities. The AI Assistant answers questions, validates assumptions, and retrieves data conversationally and through data visualizations. Together, they represent a full stack of AI tools operating under AppsFlyer’s Modern Marketing Cloud.
This report looks at what marketers are actually doing in AppsFlyer’s platform: the queries they run, the agents they configure, and the workflows they build. The findings combine quantitative aggregate results — the Top data trends section — with qualitative research across every area in the Use Cases section. Together, they offer an in-depth view of where AI adoption in marketing stands today, and where it is heading.
* All results are based on fully anonymous and aggregated data. To ensure statistical validity, we follow strict volume thresholds and methodologies and only present data when these conditions are met.
Token authentication MCP activity hits 48% share as agentic and automated use takes hold
Bearer token authentication is not a conversational interface. It authenticates automated or agentic workflows built in tools like N8N, Make, and command-line clients. These range from scheduled data pulls to fully agentic systems that reason across tools, querying the MCP server programmatically rather than through a chat window.
The rise in the the share of accounts connecting via token authentication jumped from 13.6% in December 2025 to 47.7% by May 2026 (a 250% increase), demonstrating how the use case for MCP is shifting from exploration to production, as a more technically advanced user base increasingly adopts workflow automation over direct chat interfaces. This is especially true for marketers, who can now build automations and agents without relying on developers or analysts.
Claude and Claude Code together tell the other side of that shift. Claude held a share of 19% to 32% across the period, growing steadily as the interactive layer for marketers, analysts, and developers querying the API conversationally. Claude Code nearly tripled from 3.8% to 9.9%, a signal that developers are increasingly engaging with MCP from within their build environment. The two together grew 85% from 22.7% to 42%, suggesting the programmatic and conversational layers are both expanding.
Claude’s rise reflects a broader market dynamic. By mid-2025, Anthropic’s enterprise revenue had surpassed OpenAI’s, despite ChatGPT’s commanding consumer lead — roughly 70% of ChatGPT usage is non-work-related. The more precise distinction is that Claude dominates the API and agentic coding segment specifically, where Anthropic held an estimated 54% of the enterprise coding market by early 2026. In an MCP context, which is inherently a developer and analyst interface, that advantage is likely amplified.
On the regional side, APAC accounts for the steepest token authentication climb, moving from 13% to 63.7% (+390%), where nearly two in three interactions now come from automated or agentic pipelines. North America follows a similar arc, rising from 10% to 52.1% (+420%). EMEA is the outlier: token authentication’s share contracted 25%, from 19.1% to 14.4%, where Claude dominates at 54.5% in May, suggesting the EMEA user base skews toward direct, conversational API use over workflow automation.
The center of gravity for MCP adoption has two sides: token-authenticated pipelines on one; interactive developer and analyst sessions on the other, with both experiencing an increase as the user base is maturing and self-selecting toward developer tooling over time.
The concentration of usage across MCP hosts reinforces this picture: 84% of accounts connect through a single host, with fewer than 15% using two or more. This points to a user base still largely in the “found one entry point” phase as most accounts have identified a tool that fits their workflow and have not yet expanded beyond it.
Explore the ‘use cases’ section for inspiration on MCP usage (see navigation at the bottom of the screen).
Share of companies by MCP host
Number of MCP hosts distribution
MCP account base grows 12x in six months
The number of companies actively using AppsFlyer’s MCP grew 12x in six months. Growth was not linear: the sharpest single-month jump came in March 2026, when the account count rose 188%. That timing is not coincidental.
The publication of Anthropic’s official 2026 MCP roadmap on March 9, combined with the protocol’s December 2025 donation to the Linux Foundation under the vendor-neutral Agentic AI Foundation — backed by AWS, Google, Microsoft, Salesforce, and Snowflake — removed the single-vendor risk that had slowed enterprise adoption. AppsFlyer’s March inflection reflects companies responding to MCP becoming infrastructure, not an experiment. In addition, with the release of Claude’s Cowork, marketers can vibe code using MCP connections.
APAC is the dominant region throughout, growing to represent 48.8% of the total by May. North America grew fastest in proportional terms, surging 1,659% increase with much of that acceleration coming in May, when it nearly tripled from the previous month. EMEA grew more steadily while LATAM remains the smallest region but has grown consistently.
The regional distribution points to where AI-driven data access has gained the most organizational traction. APAC’s share is consistent with its leading role in token authentication adoption seen in the previous section — technically advanced teams in the region appear to have moved quickest from discovery to production-grade programmatic usage. North America’s late acceleration suggests a second wave of adoption may still be building.
Companies connecting MCP by region
Half of MCP accounts return within day 7 or later, with a third still active on day 30
Retention in the first 24 hours is strong: 66% of accounts that ran their first MCP query returned on day 1 or later, and 53.4% were still active by day 7 or later. For a developer and analyst tool used on demand rather than daily habit, those early numbers suggest MCP is providing enough immediate value to bring users back within the first week. By day 30, 32.7% of accounts had returned at some point within that window — meaning nearly one in three remained active across the full first month.
The daily return rate (the share of accounts that came back on any specific day) holds between 24% and 19% from day 1 through day 18, with no pronounced downward drift over that window. Accounts that move past initial exploration appear to settle into a recurring usage pattern rather than gradually fading out. The implication is that early retention, if achieved, tends to hold.
The weekly data points to week 5 as the key behavioral inflection. The share of accounts returning on a given week drops from 23.3% at week 5 to 13.7% at week 6, a 41% decline and the steepest single-step drop in the dataset. This is likely where casual or exploratory accounts disengage, leaving a more committed core. By week 8, 11.2% of accounts remain active on a weekly basis.
The sharp drop at week 11 is not behavioral, as it reflects data truncation: accounts that first connected in the final weeks of the observation window simply had not yet had enough time to return at later intervals, so they are absent from the later data points, causing the numbers to fall steeply.
MCP retention rate
Agents never rest: Automation runs all week, with weekends at 70% of weekday volume
Agent and automation MCP usage does not follow a traditional working week like humans. Weekend activity averages 70% of weekday volume, a modest dip rather than the near-zero drop typical of tools tied to human working hours.
Automated and agentic pipelines authenticated via token authentications do not observe a five-day week. Workflows built in tools like N8N, Make, and command-line clients run on schedules set by the teams that built them, not by the calendar. The contrast is visible in AppsFlyer’s own AI assistant, which is entirely human-led: weekend usage there drops sharply and becomes negligible, a pattern that makes the MCP weekend baseline stand out by comparison.
The consistent weekend activity is, in that sense, a byproduct of the same shift visible in the monthly data: as token authentication usage has grown to nearly half of all activity, the platform has become less dependent on human-initiated sessions and more driven by always-on automation.
Explore the ‘use cases’ section for inspiration on agent usage (see navigation at the bottom of the screen).
Daily MCP call volume *
Performance reporting leads agent adoption, with usage deepening over time
In AppsFlyer’s Agent Hub, Marketers can choose from a library of pre-defined agents. Their top choice is ‘Weekly Performance Report’ with 38.6% of all setups, reflecting the most universal need: automated, recurring visibility into performance data. ‘Detect Setup Issues’ follows at 24.7% — a broad, near-universal need for any team that cares about measurement quality. Together they account for nearly two thirds of all configurations.
‘Optimize Anti-Fraud’ Strategy at 14.2% serves a more specific audience: accounts running AppsFlyer’s Protect360 who want proactive fraud detection rather than reactive reporting.
Creative and anomaly-focused agents ‘Spot Creative Opportunities’ and ‘Detect Performance Anomalies’ sit below 5% each, likely reflecting their more specialized scope.
Among active accounts using the platform across both periods, the average number of agent types configured grew from 2.74 to 2.92. More telling is the distribution shift: accounts using only one agent type dropped 42%, from 16.7% to 9.7%, while those using three or more grew steadily. This points to gradual deepening as companies that stayed on the platform expanded into additional agent types over time rather than settling into a single workflow.
Distribution of agent configurations by type
Share of accounts by number of agent types used
One in five questions is a data query as users go deeper on implementation and analysis
The largest category, at 36% of 37,082 analyzed questions from AppsFlyer’s AI assistant, is platform navigation and how-to: users asking where to find a feature, how to complete a task, or what a setting does. The fact that the assistant absorbs this volume is significant from an operational standpoint, but it is the least surprising finding. The more telling signals sit in the categories below it. And across 74% of the questions, they demonstrate growing sophistication among the target audience.
One in five questions asks the assistant to retrieve or analyze performance data. At 20.1%, users are not asking how to use the platform, they are asking it to surface their own numbers: installs by source, ROAS by campaign, cohort breakdowns by geo, period-over-period comparisons. This is analyst behavior, not support behavior, and it points to a user base that has found a faster path to insight through conversation than through the dashboard.
The technical profile of the user base comes through across the next three groups. Attribution and measurement questions account for 9.7%, technical setup and SDK integration for 7.1%, and deep linking and OneLink configuration for 6.3%. Together, these three categories represent 23.1% of all questions — nearly matching data querying in volume, and pointing to a user base comfortable with implementation-level detail.
The questions involve attribution windows, postback configuration, server-to-server event setup, and OneLink troubleshooting. This is not a general marketing tool audience asking surface-level questions; it appears to be an audience that understands how the measurement layer works and is using the assistant to go deeper into it.
Chart and trend interpretation accounts for 3.9%, and anomaly investigation for 2.4%. Both reflect the assistant embedded directly in the analytics workflow: users sharing a live chart or a data pattern and asking the assistant to explain it, rather than treating it as a separate consultation tool.
Explore the ‘use cases’ section for inspiration on AI assistant usage (see navigation at the bottom of the screen).
Share of AI assistant question types
- Real-time performance insights [Square]
-
Real-time performance queries in the meeting room. Square’s primary use case is replacing the manual dashboard lookup with a custom dashboard built via MCP which includes live charts, data visualizations, and the ability to query AppsFlyer data on demand, all in a single view that’s ready to present.
When in a meeting with a programmatic partner and facing an unexpected question about performance, the AppsFlyer MCP connected to Claude surfaces the answer in real time, eliminating the need for a manual report pull. The queries run in this context include which app types drive the best install or event outcomes, how individual programmatic networks compare on top-of-funnel quality versus churn, and revenue breakdowns that would otherwise take hours to compile.
Connecting AppsFlyer data with internal sources. The second layer is joining the AppsFlyer MCP with proprietary internal data. Square runs city-level revenue data that can’t be shared externally, but by connecting it alongside the AppsFlyer MCP through Databricks, the team can ask questions that cross both datasets — for example, which merchant categories perform better in specific months, and whether that should inform creative timing. The MCP handles the AppsFlyer side; the internal connection handles the proprietary side; the AI joins them without requiring SQL knowledge from the end user.
Running multiple MCPs in parallel. Square connects multiple MCPs simultaneously: the AppsFlyer MCP for attribution and event data, Google UAC and Apple Search Ads directly for spend, then the AppsFlyer MCP again for aggregated events. The joining factor is the common media source dimension. It is a manually assembled architecture, but one that becomes straightforward once the common key between datasets is identified.
Cleaning up historical naming conventions. A more operational use case is using the MCP to rationalize naming convention inconsistencies in historical data. When OneLink naming has drifted across teams over time, generating different capitalizations, underscores, and spaces, querying through the MCP helped surface and clean up those patterns without a manual audit.
“I can ask AI to pull performance data and dive straight into revenue insights. What used to take hours now takes under 2 minutes.” Sara San Antonio, Sr. Global Marketing Mobile Manager, Square
Watch the webinar - Cohort progression analysis at daily frequency [Supersonic Studios]
-
From multi-dashboard investigation to a two-minute query. Supersonic’s primary MCP use case is eliminating the gap between having a performance question and getting an answer. Before, a UA manager needing a ROAS summary for a stakeholder update had to pull data from multiple sources, format it, and write the narrative manually. With the AppsFlyer MCP connected to the LLM of their choice, the same request is answered in plain language in minutes instead of hours.
Cohort progression analysis at daily frequency. The deeper application is cohort monitoring at a depth manual work cannot sustain. Supersonic measures ROAS progression from D0 through D7 and D30, comparing current cohort trajectories against historical patterns for the same title and campaign. A cohort where D0 ROAS looks healthy but the progression to D3 is lagging behind prior cohorts is already signaling a problem. However, spotting that change across every active title and campaign on a daily basis was not realistic manually. MCP makes it a conversational query rather than a multi-dashboard investigation.
Connecting AppsFlyer data with additional sources. Supersonic also connects the AppsFlyer MCP alongside internal data sources to answer questions that cross datasets. The specifics of what those sources contain are not public, but the pattern matches the broader use case: MCP as a joining layer between AppsFlyer’s attribution and revenue data and proprietary internal data the team needs in the same answer.
Getting the data right first. Early experiments with raw data fed directly to the LLM produced unreliable outputs — inconsistent field names and overlapping revenue dimensions caused the model to guess at calculations, and the team lost trust quickly. Supersonic’s fix was to pre-aggregate data on the BI side for each specific use case before passing it through MCP. The LLM receives something scoped and precise, and the outputs match numbers the team already recognizes in their own dashboards.
“You can actually take MCP and build your own agents and workflows. This is a part that a human is still in the loop and it’s really interesting to discover.” Ofer Regev, Product Manager AI and Automation, Supersonic Studios
Open case study - Pre-programmed workflows using a claude.md file [Shamanth Rao]
-
Building a performance analyst that runs on demand. This MCP use case moves beyond ad-hoc querying into pre-programmed workflows. Using a claude.md file — a set of plain-language instructions stored in the same folder as the MCP connection — it is possible to define a multi-step analytical routine that runs end-to-end when triggered by a single phrase. “Give me my performance check” is not a query. It is activating a pre-built analyst.
What the workflow actually does. The example routine runs eight steps automatically: pull the last seven days of data from AppsFlyer for each paid channel, calculate ROAS, flag the channels with the lowest ROAS, rank all channels by efficiency, compare paid versus organic performance, identify any paid channel where ROAS is negative, recommend which channels to scale, and close with a budget reallocation suggestion. The output is a structured report, not a raw data dump. The whole sequence runs from one prompt.
The difference from conversational querying. Rather than asking the MCP questions as they arise, the claude.md pattern is different in kind: it encodes analytical judgment into the system in advance, so the same rigorous review runs every time, not just when someone thinks to ask. The workflow can also be made progressively smarter — adding a rule like “compare iOS versus Android performance” updates the routine permanently without rebuilding anything. It is closer to building a custom analyst than using one.
“[With MCP] you can activate a sequence of steps just by asking for one single phrase which you have pre-programmed before. That is the beauty of claude.md.” Shamanth Rao, ROCKETSHIP HQ
Watch the video - Cross-app portfolio analysis [gaming company]
-
Querying across an entire app portfolio at once. For companies managing multiple apps, the standard MCP workflow where you query one app, get an answer, and move to the next does not scale. With MCP, the company queries across the full portfolio simultaneously, asking questions that only make sense when all titles are in view at once. Which apps are underperforming in a specific geo relative to their global average? Where is early D0 ROAS strongest and not being followed by proportional spend? These are portfolio-level questions that dashboard-by-dashboard review answers far less efficiently.
Identifying cannibalization and concentration risk. A less obvious but high-value application is surfacing where apps within the same portfolio are competing against each other for the same users. Two titles targeting a similar audience in the same geo through overlapping channels will bid against each other, inflating CPIs across both. MCP can surface that overlap in titles, geos, and channels, and frame it as a reallocation opportunity rather than leaving it buried in individual campaign views that no one is comparing side by side.
Turning portfolio signals into prioritization. The output is not just data, it’s a ranked view of where to concentrate attention. Rather than a UA manager cycling through ten dashboards to form a mental picture of where the portfolio stands, a single MCP query returns a structured comparison: which titles are over-indexed for their performance level, which are under-resourced relative to their cohort signals, and where the highest-confidence scaling opportunity sits right now. The portfolio becomes legible as a system, not a collection of individual campaigns.
- Anomaly detection agent [Supersonic Studios]
-
When the signal is buried three levels down. The anomaly that costs the most is rarely the one that shows up on the dashboard. At Supersonic, the monitoring challenge was not spotting obvious top-line drops, but rather finding the performance issues that were invisible at the summary level but compounding underneath. A game’s overall revenue could look stable while a specific campaign, geo, or KPI was already shifting in a direction that would become a problem days later.
An agent found what a human would have missed. A real example from Supersonic’s portfolio: a game experienced a performance drop caused by an in-game change. The top-line revenue had not moved dramatically enough to trigger any alert. An anomaly detection agent running on that campaign drilled through the data at a deeper KPI level, found the deviation, and sent a Slack alert with the specifics. The team investigated and resolved it the same day before the signal had surfaced in any dashboard view.
“We had an agent running on that game. It found the core of the issue and just showed, in a simple alert, that something happened, and now the human can take that and act on it. It was overlooked because it was not the main KPI and was not seen clearly on the dashboard. But the agent drilled down again and again until it found the issue.”
Ofer Regev, Product Manager AI and Automation, Supersonic Studios
The case for continuous, not periodic, monitoring. The value is not just in finding issues faster — it is in finding issues that periodic human review would never catch at scale. With a portfolio of dozens of titles and hundreds of campaigns, a UA manager cycling through dashboards manually will always miss something. An agent running continuously does not get tired, does not skip a title because another one needed attention, and does not wait for the weekly report to flag what changed on Tuesday.
“Having something do that for us and alert us when something happens is gold. We have the ability to act really fast and avoid revenue loss.”
Ofer Regev, Supersonic Studios - Agents work on weekends [gaming company]
-
The coverage gap that runs every weekend. In mobile gaming UA, spend does not pause for the weekend but analyst coverage does. Campaigns running across Google and TikTok continue to pace, shift, and potentially drift through Saturday night and into Sunday with no human watching the numbers.
Continuous monitoring across the clock. One leading EMEA gaming UA team deployed Agent Hub to close that coverage gap. Agents monitor pacing and performance signals around the clock across both Google and TikTok, detecting deviations from expected patterns in real time and triggering corrective actions in the moment rather than queuing them for the next working day. The system does not wait for a human to open a dashboard. It acts on the signal when the signal appears.
40% of weekend spend protected at 2 am. The outcome that validated the approach came at 2am. An agent caught a budget pacing issue mid-weekend that would have silently drained an estimated 40% of the weekend budget before any analyst would have seen it.
“The agent caught a budget pacing issue at 2 am that would have wasted 40% of our weekend spend. That would never have happened manually.”
Performance Marketing Lead, leading EMEA gaming UA team
The result reframed how the team thinks about coverage. The constraint was never analyst skill, it was analyst availability. An agent running continuously removes the dependency on human presence during the hours when mobile gaming campaigns are often at their most active. - Optimize against fraud [Nomad]
-
Fraud that evolves faster than manual rules can follow. Ad fraud does not stand still. The patterns that triggered yesterday’s rules may have already mutated by the time a human analyst reviews the logs. For growth teams running significant paid budgets, the gap between detection and response is where spend disappears, often in a steady drain that only becomes visible in hindsight.
AI that detects, deters, and recovers. AppsFlyer’s AI-enhanced fraud protection operates continuously across the attribution data, learning patterns in real time rather than waiting for rules to be updated. This enhanced detection, which also includes rapid responsiveness, improved accuracy and stability, and a lift in real time detection leads to a significant uplift in performance compared to non-AI detection.
The results are clear: 7X higher detection accuracy, 8X faster recovery time when fraud is identified, and 14X longer deterrence — meaning fraudsters are kept out for significantly longer before finding a new vector. The Optimize Anti-Fraud Strategy agent surfaces these signals proactively, flagging early indicators and recommending actions before the damage compounds.
Nomad: cleaner data as a strategic input. For Nomad, the value of AI-enhanced fraud protection extended beyond blocking bad spend. Gabriel Sampai, Senior Growth Manager at Nomad, frames it as a data quality problem as much as a fraud problem.
“AppsFlyer’s AI not only will help our bottom-line revenue numbers, but will give us a clearer picture of our data sets, enabling us to evolve our marketing strategies moving forward.”
Gabriel Sampai, Senior Growth Manager, Nomad - Spot Creative Opportunities [gaming studio]
-
The blind spot in the creative workflow. At a mid-size mobile gaming studio running UA campaigns across six networks, creative performance review happened network by network, manager by manager. The team member running TikTok and Mintegral had no visibility into what was performing on Google or AppLovin. When a new creative began trending on TikTok after its first seven days, nobody was in a position to ask whether it was running on the other networks. By the time the weekly creative review surfaced it, the scaling window had already narrowed.
What the agent found that the team had missed. After deploying the ‘Spot Creative Opportunities’ agent, the studio began receiving proactive alerts on creatives showing strong early signals across their full network mix — not just the ones any individual manager was watching. In the first weeks of use, the agent surfaced a creative trending strongly on Mintegral that had not been activated on two other networks where the audience profile matched. The team activated it within 24 hours. The analysis that enabled that decision would previously have required someone to manually cross-reference performance data across accounts, which was a task that rarely happened between weekly reviews.
Speed-to-insight on assets with a limited window. Creative performance in mobile gaming follows a decay curve. The window between a new asset showing early strength and that asset reaching saturation is often measured in days, not weeks. An agent monitoring performance continuously and alerting the team to emerging winners compresses the time between signal and spend decision, which is where the value compounds.
- Speed and confidence lift gaming studio
-
From long investigations to fast answers. For Peaksel, a mobile gaming studio managing campaigns across multiple channels, the AI assistant’s primary value is compression, taking what used to be a lengthy investigation and reducing it to a directed, structured answer. Daily performance questions, attribution setup issues, and technical validation tasks that previously required digging through documentation, opening support tickets, or running manual checks now have a faster first stop.
Validation without the friction. A representative use case is Meta AEM eligibility. Confirming whether a setup meets the requirements, identifying what is missing, and knowing what to fix involves multiple conditions and configuration checks. The AI assistant surfaces a clear checklist rather than requiring the team to reconstruct the answer from documentation each time. The outcome is not just speed, it is confidence. The team acts on the guidance rather than second-guessing a manual interpretation.
Supporting judgment, not replacing it. Peaksel’s framing of the tool is deliberate: the assistant removes friction and uncertainty, but human judgment remains in the decision. It is a faster path to the right question, not an autonomous decision-maker.
“The AI assistant helps us validate assumptions and resolve technical issues much faster. Instead of long investigations, we get clear guidance that saves time and removes uncertainty.”
Milorad Grkovic, UA Lead, Peaksel - Data querying & reporting examples
-
One in five questions asks the assistant to retrieve and analyze performance data directly. Users are asking the assistant to surface their numbers: ROAS by campaign, cohort curves by media source, retention trends by country.
For these queries, the assistant compresses what would otherwise require building a report, running an export, or waiting for an analyst into a conversational request answered in seconds.
Examples:- “I would like to have daily ROAS D7 trend, breakdown by media source, cohort data, last 30 days”
- “Show ROAS D7 and ROAS D30 for my app last 30 days broken down by country. Top 15 countries by spend”
- “For Triumph: Play for Cash only, what are the D1, D7, D30, and D60 user retention rates from January 2025 through February 2026? Show monthly trend if possible”
- “Give weekly ROAS breakdown by campaign for D7, D14, and D21 for this media source. Consider baked data only”
- “Can you get me paid_imp_18 unique user conversion rate (D1, D7, D14) by media source?”
- Attribution & measurement examples
-
This group reflects the technical depth of the user base. These are configuration decisions with real downstream consequences: whether to enable view-through attribution, how to set re-engagement lookback windows, why impression-attributed installs appear when the setting is off.
The assistant provides a faster path to a confident answer than documentation alone, and catches configuration gaps before they distort the data.
Examples:
- “Re-engagement view-through attribution is set to off — should it be on, and is 30 days suitable given your suggestion to apply 7 days to the re-engagement click-through lookback window?”
- “Should I enable inactivity window or ignore impression-based conversions for re-engagements if I have 75% of conversions for Facebook under remarketing and 80% of these are impression-based?”
- “I didn’t enable view-through attribution for Meta ads, but in AppsFlyer installs raw data there are still impression-attributed touch types for Facebook ad installs. What’s the reason?”
- “For these top media sources, have I enabled click-through attribution window, view-through attribution window, and re-engagement window — check and tell me”
- “My meta ad campaign goes to a Typeform quiz. After they submit, they receive a OneLink to install the app. How should I set up the links to have correct impression and click attribution and allow for postback events post-install?”
- Anomaly investigation examples
-
The most sophisticated questions in the dataset come from this group. Users are forming hypotheses and asking the assistant to test them: is this a payback window issue or a monetization gap? Is this delayed ROAS or real LTV erosion? Is creative fatigue explaining the D7 drop? The assistant acts as a sounding board that can pull data to validate or disprove the hypothesis in the same exchange.
Examples:
- “Break Google down by campaign to see if specific markets are diluting ROAS. Compare D7 vs LTV ROAS to check whether this is a payback window issue vs a fundamental monetization gap”
- “Overlay D7 ROAS vs D3 to determine whether this is delayed monetization or real LTV erosion”
- “What is happening to short form submit in Canada from 1 Dec to date? Explain trends, patterns and possible issues with installs, short forms and install-to-short form conversion rates”
- “Can you analyze weak creatives dynamically and check if ROAS (D1, D7, D30) are more or less even or if there is a positive trend?”
- “Should we compare D7 vs D1/D30 retention to see quality decay by campaign?”
84% of accounts connect through a single MCP host, and the 12x growth in six months suggests the barrier to starting is lower than most teams assume. Consider identifying one repetitive, data-heavy workflow — a weekly performance check, a channel efficiency review — and automating it first. The compounding value comes with expansion, but the entry point is one workflow.
Token authentications now account for nearly half of all MCP activity, and weekend call volume running at 70% of weekday levels confirms that the most active use cases do not depend on a human being present. Teams still relying solely on conversational interfaces should explore scheduled, programmatic workflows as the next step in their MCP adoption.
Among active Agent Hub accounts, the share using only one agent type fell 42% over the observation period, while average agent types per account grew from 2.74 to 2.92. Rather than deploying agents broadly and shallowly, consider going deeper in the areas already in use — particularly the move from defensive monitoring toward optimization and opportunity surfacing.
Half of accounts return within a week, and the daily return rate holds flat through the first three weeks for those that do. The data suggests that early value is the determinant — accounts that find a reason to return in the first few days tend to stay. Onboarding investment in the first week is likely to have an outsized effect on long-term retention.
The most sophisticated users in the dataset treat the AI assistant as an analytical partner — forming hypotheses and asking it to test them, not just retrieve data. The quality of insight is proportional to the quality of the question. Teams using the assistant primarily for navigation and how-to queries should explore its capacity for cohort analysis, anomaly diagnosis, and attribution validation.
