How to Use the AppsFlyer (Pull API) MCP in LangChain

Q: Can my LangChain agent compare reports from the AppsFlyer (Pull API) tools?

Yes. You can have your agent call getdailyreport and getuninstallsreport in sequence, then use a final step in the chain to compare the results. The agent can then summarize the findings or flag discrepancies based on your logic.

Q: Does this MCP Server let me see raw user data?

Yes, it provides access to raw data reports. The getinstallsreport, getuninstallsreport, and getinappeventsreport tools all fetch raw, row-level data directly from the AppsFlyer Pull API for detailed analysis.

Build marketing data chains in LangChain. Connect campaign performance directly to user actions with live AppsFlyer data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AppsFlyer (Pull API) MCP to LangChain

Create your Vinkius account to connect AppsFlyer (Pull API) to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup AppsFlyer (Pull API) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Attribution Reports Together

Start by pulling a high-level summary with `get_partners_report`. Your LangChain agent can then parse the output, pick the top-performing media source, and automatically call `get_installs_report` filtered for just that partner. You're building a flow, not just running a command. This isn't about just fetching data. It creates an investigative sequence. Your agent can compare daily performance (`get_daily_report`) against uninstall trends (`get_uninstalls_report`) in the same chain, giving you a complete picture of campaign health without manual work. Every step is observable through LangSmith.

Dig Into Raw Event and Install Data

Go beyond the aggregates. Use `get_in_app_events_report` to get the raw data feed of what users are actually doing inside your app. Your agent can process this stream, looking for specific event patterns or anomalies that signal fraud or opportunity. Combine this with `get_installs_report`. A LangChain agent can correlate specific install cohorts with their downstream in-app behavior, all within a single, traceable execution chain. This MCP server makes raw attribution data another link in your agent's logic.

Automate Geo-Performance Checks

The `get_geo_report` tool gives your agent country-level performance data. You can build a chain that automatically checks performance in key markets every morning and flags any that drop below a set threshold. If a specific country's metrics fall, the agent can trigger another part of the chain. Maybe it pulls the raw `get_installs_report` for that region to see if a specific partner is the cause. This turns your agent into an automated market analyst.

Setup guide

Set up AppsFlyer (Pull API) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes AppsFlyer (Pull API) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "appsflyer-pull-api-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent AppsFlyer (Pull API) transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect AppsFlyer (Pull API) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about AppsFlyer (Pull API) MCP in LangChain

You design your agent to use the output of one tool call as the input for the next. For example, get a partner ID from `get_partners_report` and feed it directly into a more detailed query using `get_installs_report`. LangChain's expression language makes this straightforward.

Yes. You can have your agent call `get_daily_report` and `get_uninstalls_report` in sequence, then use a final step in the chain to compare the results. The agent can then summarize the findings or flag discrepancies based on your logic.

You don't have to handle it. Vinkius provides a single endpoint token for your MCP server. You just pass that token when you initialize the MCP client in your LangChain code, and all tool calls are authenticated automatically.

Yes, it provides access to raw data reports. The `get_installs_report`, `get_uninstalls_report`, and `get_in_app_events_report` tools all fetch raw, row-level data directly from the AppsFlyer Pull API for detailed analysis.

Your agent's requests for attribution data and install reports are processed in an ephemeral, sandboxed environment on Vinkius. Your API keys are stored securely by Vinkius, never exposed to the agent. All data in transit is encrypted, and no report data is stored after the request is complete.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript