AppsFlyer (Pull API) MCP. Pull raw attribution data for user behavior analysis.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
AppsFlyer (Pull API) MCP Server gives your AI agent direct access to raw and aggregate mobile attribution data from AppsFlyer.
It lets you pull specific reports—like daily performance, install counts, or in-app events—using natural language. You get structured CSV data for deep dives into user behavior, campaign performance, and LTV tracking.
It's built for data analysts who need to move beyond basic dashboards.
What your AI agents can do
Get account check
Verifies if your AI agent can connect to and access your AppsFlyer account data.
Get daily report
Pulls a summary of your app's performance metrics for a specific day.
Get geo report
Generates a performance summary broken down by geographical region.
Verifies that your AI client can successfully connect and authenticate with your AppsFlyer account.
Retrieves a summary of your app's performance metrics for a specific day.
Generates aggregate performance metrics, broken down by geographical area.
Downloads raw, granular data for every in-app event recorded during the specified time period.
Retrieves raw data detailing non-organic app installs, excluding paid or tracked sources.
Generates aggregate metrics, grouping performance data by the marketing partner or source.
Downloads raw data detailing app uninstalls, helping track user retention metrics.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
AppsFlyer (Pull API) MCP Server: 7 Tools for Attribution Data
Use these tools to retrieve raw and summarized performance data, covering everything from user installs and in-app events to geographic and partner performance metrics.
019d7551get account check
Verifies if your AI agent can connect to and access your AppsFlyer account data.
019d7551get daily report
Pulls a summary of your app's performance metrics for a specific day.
019d7551get geo report
Generates a performance summary broken down by geographical region.
019d7551get in app events report
Downloads raw data for every in-app action, like purchases or level completions.
019d7551get installs report
Retrieves raw data detailing non-organic app installs.
019d7551get partners report
Generates a performance summary grouped by the marketing channel that drove the install.
019d7551get uninstalls report
Downloads raw data for every instance of an app being uninstalled.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with AppsFlyer (Pull API), then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Yo, this server hooks your AI agent straight into your raw and aggregated mobile attribution data in AppsFlyer. You'll pull specific reports—like daily performance, install counts, or in-app events—just by talking to it. You get structured CSV data for deep dives into user behavior, campaign performance, and LTV tracking. It's built for data analysts who gotta get past those basic dashboards.
get_account_checklets your agent verify if it can connect and access your AppsFlyer account data.get_daily_reportpulls a summary of your app's performance metrics for a specific day.get_geo_reportgenerates a performance summary broken down by geographical region.get_in_app_events_reportdownloads raw data for every in-app action, like purchases or level completions.get_installs_reportretrieves raw data detailing non-organic app installs.get_partners_reportgenerates a performance summary grouped by the marketing channel that drove the install.get_uninstalls_reportdownloads raw data for every instance of an app being uninstalled.
How AppsFlyer (Pull API) MCP Works
- 1 Tell your AI client exactly what data you need and the date range. For example, 'Show me the daily performance report for the last 30 days.'
- 2 The agent calls the appropriate tool (e.g.,
get_daily_report) and passes the necessary parameters, like start and end dates. - 3 The system returns a structured CSV report containing the requested attribution metrics, which your agent can then read and interpret.
The bottom line is, your AI client speaks to the AppsFlyer API, pulls the raw data, and gives you a clean file ready for analysis.
Who Is AppsFlyer (Pull API) MCP For?
This is for the data analyst who spends half their week clicking between dashboards and copy-pasting numbers into a spreadsheet. You need raw data and the ability to query performance across different dimensions (geo, partner, day) without building custom reports from scratch. It’s built for people who need to prove ROI and track complex user journeys.
Retrieves raw event logs (get_in_app_events_report) and combines them with install data (get_installs_report) to build user funnels and calculate true LTV.
Quickly audits campaign performance and install trends by pulling reports for specific media sources (get_partners_report) and tracking daily performance (get_daily_report).
Monitors daily and geographic trends using tools like get_geo_report to optimize ad spend and target new regions.
What Changes When You Connect
- See your install funnel from start to finish. Use
get_installs_reportfor non-organic installs, then combine that data withget_in_app_events_reportto track user actions and lifetime value. - Audit campaign spend by source.
get_partners_reportgives you aggregate performance metrics grouped by the media partner, letting you see which channels are performing. - Track retention and churn. Use
get_uninstalls_reportto see exactly when and why users left, paired withget_daily_reportto spot retention dips. - Focus on specific campaigns. Instead of looking at everything, use the date parameters on any report (e.g.,
get_geo_report) to limit the scope to one campaign's window. - Simplify complex data pulls. Need to know how performance changes by state or country?
get_geo_reportpulls that aggregate data without needing a separate geo-specific tool. - Verify access quickly. Always start with
get_account_checkto confirm your AI agent can connect and read data before running large, time-consuming reports.
Real-World Use Cases
Determining Campaign ROI After a Major Launch
The UA Manager needs to know if the new paid ad campaign was worth the spend. They ask their agent to run get_partners_report for the last month, comparing the performance metrics of the new partner against the historical average. The agent pulls the data, isolates the new source, and provides the numbers for the final ROI calculation.
Investigating a Sudden Drop in User Engagement
The Product team notices a sudden dip in 'purchase' events. They ask the agent to pull get_in_app_events_report for the last 48 hours. The agent returns the raw event logs, allowing the data analyst to cross-reference the specific actions with the get_daily_report to identify when the drop started.
Mapping User Journey Failures
A Growth Marketer suspects a bug is causing users to leave right after installation. They ask the agent to run get_installs_report followed by get_uninstalls_report. By comparing the timestamps and volumes, they can pinpoint the exact period where installs spiked but uninstalls followed shortly after.
Comparing Performance Across Regions
A VP of Marketing needs to see if the Southeast region is underperforming compared to the Northeast. They ask the agent to run get_geo_report for a specific quarter. The agent delivers the aggregate data, allowing the VP to immediately see the regional differences and allocate budget accordingly.
The Tradeoffs
Manually cross-referencing reports
The analyst runs get_daily_report for last month, copies the install numbers. Then they have to run get_partners_report and manually filter the dates and sources to match the first report. This takes hours and is prone to copy/paste errors.
→ Ask your agent to run both reports simultaneously, specifying the exact date range and instructing it to join the data. The agent handles the cross-referencing automatically, giving you a single, unified output.
Only looking at aggregated metrics
The marketer sees a low overall performance score on the dashboard and assumes the whole campaign failed. They miss the details because they never looked at the raw logs.
→
Don't stop at the summary. Pull the raw data using get_in_app_events_report. The granular log data tells you why the performance score is low (e.g., users aren't completing the 'purchase' step).
Ignoring the user lifecycle
The team only checks install numbers (get_installs_report) and reports success. They forget that half the users leave within a week, which means the install number is meaningless.
→
Always pair your install check with get_uninstalls_report. This gives you the full picture: how many people came in, and how many left. It shows the true retention rate.
When It Fits, When It Doesn't
Use this server if your primary need is data retrieval and structured reporting. You need to pull specific, discrete reports—like 'all events for today' or 'performance for Germany'—and put them into a structured format (CSV). Don't use this if you need real-time, continuous data streaming, or if you need to model complex causal relationships (e.g., 'if we change Feature X, what will the uninstalls be?'). For predictive modeling, look for a dedicated simulation platform. This server is for historical, verified data reporting.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by AppsFlyer. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 7 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Building a unified report from multiple dashboards is a nightmare.
Today, getting a full picture of user acquisition means logging into the AppsFlyer dashboard, running a report, downloading a CSV. Then, you jump to Google Analytics, pull a separate report, and copy-paste the numbers into a third spreadsheet to stitch them together. It's a painful, multi-system, manual process.
With the AppsFlyer (Pull API) MCP Server, your agent handles the whole thing. You ask for a combined report—for example, 'Give me the installs and the events for the last week.' The agent runs the necessary tools and delivers a single, clean, structured file.
AppsFlyer (Pull API) MCP Server: Pulling raw attribution data
The biggest time sink is running multiple report types. You have to separately request install numbers, then request event data, and then request geographic splits. This requires multiple manual steps and API calls.
Now, you just tell your agent what you need. You can ask for raw data on installs and filter it by partner, or ask for events and limit the timeframe to the last day. It's a single prompt, and you get a usable data set.
Common Questions About AppsFlyer (Pull API) MCP
How do I use the get_account_check tool with AppsFlyer (Pull API) MCP Server? +
You run get_account_check first. This verifies that your AI client has the correct API token and can successfully communicate with your AppsFlyer account before attempting to pull any large reports.
Can get_in_app_events_report handle specific event types? +
Yes, you can specify event types and filters. This tool pulls the raw data for all in-app events, allowing you to isolate specific actions like 'purchase' or 'level_complete' for deeper investigation.
What is the difference between get_installs_report and get_daily_report? +
The get_installs_report pulls raw data on non-organic installs. The get_daily_report provides a higher-level, aggregated summary of performance for a single day, making it better for quick daily checks.
How do I get performance data by media source using get_partners_report? +
You ask the agent to run get_partners_report, specifying the date range. The report aggregates metrics, allowing you to compare performance across all marketing channels or partners in one place.
How does get_geo_report specify the date range for performance data? +
You specify the date range in the request parameters. The tool accepts start and end dates, allowing you to focus the report on specific weeks, months, or quarters.
If I need non-organic installs, which tool should I use: get_installs_report or get_daily_report? +
You should use get_installs_report. This tool pulls raw data specifically for non-organic installs, while get_daily_report provides general aggregate performance metrics.
Does `get_uninstalls_report` include data on why a user uninstalled the app? +
The get_uninstalls_report provides raw data on uninstalls. It captures the event and user ID but does not include specific reasons for the uninstall.
What happens if my API token is expired when running `get_account_check`? +
If the token is expired, get_account_check returns an authentication error. You'll need to update your AppsFlyer API token and re-run the check.
How do I find my AppsFlyer API Token V2? +
Log in to AppsFlyer as an Admin, go to Security Center from the account menu, and navigate to AppsFlyer API tokens. There you can manage and copy your V2 token (JWT).
What is the 'appId'? +
The appId is the unique identifier for your app in the store. For iOS, it's usually id followed by numbers (e.g., id123456789). For Android, it's the package name (e.g., com.example.app).
Is there a limit on the number of rows returned? +
Yes, AppsFlyer Pull API limits raw data reports to 200,000 rows. If your data exceeds this, try narrowing the date range of your request.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Kitetags
Generate optimized hashtags for Instagram and TikTok posts with AI that analyzes trending tags and maximizes reach.
Kit (ConvertKit) Alternative
Automate your creator marketing — manage subscribers, tags, and forms via AI.
Bazaarvoice
Analyze and manage user-generated content via Bazaarvoice — list products, reviews, and customer questions directly from any AI agent.
You might also like
Buzzsprout
Manage your podcast via Buzzsprout — track episodes, monitor plays, and manage content directly from any AI agent.
OpenSky Network
Track real-time flights, view aircraft states, and get airport arrivals/departures via OpenSky API.
Common Room
Unify community signals from Slack, Discord, GitHub, and social media to identify your most engaged users and advocates.