How to Use the AppsFlyer (Pull API) MCP in OpenAI Agents SDK

Q: How does the AppsFlyer (Pull API) integration handle tool caching in OpenAI Agents SDK?

Set the cacheToolsList parameter to true during initialization. This prevents the SDK from repeatedly querying the server for the tool schema on every run, reducing latency for your production agents.

Q: How does AppsFlyer (Pull API) handle credential failures within OpenAI Agents SDK?

The getaccountcheck tool will fail during your agent's initial setup phase. You can configure your agent to run this check first, halting execution and alerting your team before running expensive reporting tasks.

Pull real-time marketing attribution data directly into your OpenAI Agents SDK workflows with zero manual scripting.

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 OpenAI Agents SDK

Create your Vinkius account to connect AppsFlyer (Pull API) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run audited AppsFlyer reports inside OpenAI Agents SDK.

Your production agents can pull daily marketing performance numbers using `get_daily_report` to spot sudden drops in conversion rates via this MCP Server. The OpenAI framework lets you set strict validation rules so the agent never pulls massive raw datasets when a simple aggregate summary is all it needs. If the agent detects an anomaly, it uses `get_partners_report` to isolate which media source is underperforming. You get full execution tracing inside your OpenAI dashboard, so you can audit every single tool call without guessing what your agent did.

Trace uninstalls and installs with complete safety.

When marketing teams need the raw numbers behind a campaign shift, your agent calls `get_installs_report` and `get_uninstalls_report` to map the exact user journey. The SDK coordinates these heavy lookups safely, preventing your agent from making recursive, expensive API requests. By setting up specialized agent handoffs, one agent can handle the raw data gathering while another runs the analysis. This keeps your production system fast and prevents single-agent token limits from choking on large CSV payloads.

Monitor post-install actions using this MCP Server.

Tracking user value does not stop at the install. This MCP Server lets your agent trigger `get_in_app_events_report` to see exactly what users do after they download your mobile app. Before executing the tool, the SDK checks your pre-defined guardrails to ensure the request parameters fall within safe date ranges. You get clean, verified event logs delivered straight to your backend system without writing custom API integration code.

Setup guide

Set up AppsFlyer (Pull API) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all AppsFlyer (Pull API) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives AppsFlyer (Pull API) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate AppsFlyer (Pull API) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="AppsFlyer (Pull API) Agent",
            instructions="You have access to AppsFlyer (Pull API) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the SDK and instantiate the streamable HTTP server parameter pointing to the Vinkius endpoint. Pass this instance directly into your Agent constructor using the `mcp_servers` list. The client auto-discovers all seven tools immediately.

Yes, but you should configure agent handoffs for big files. Use one agent to fetch `get_installs_report` and another to parse the output. This prevents context window bloat and keeps your runs highly efficient.

Set the `cacheToolsList` parameter to true during initialization. This prevents the SDK from repeatedly querying the server for the tool schema on every run, reducing latency for your production agents.

The `get_account_check` tool will fail during your agent's initial setup phase. You can configure your agent to run this check first, halting execution and alerting your team before running expensive reporting tasks.

Your raw install logs, in-app event counts, and uninstall metrics stay within your local environment and the secure Vinkius sandbox. No attribution data is stored on external servers or used to train OpenAI models.

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