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

Q: How can I make two AutoGen agents use different tools from the AppsFlyer (Pull API) server?

When you configure each AssistantAgent, you pass a specific list of tools to its constructor. Give your 'analyst' agent the getdailyreport tool, and give your 'critic' agent the getuninstallsreport tool. They will only use the functions they are assigned.

Let your AutoGen agents debate marketing strategy using live data from your AppsFlyer account.

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 AutoGen

Create your Vinkius account to connect AppsFlyer (Pull API) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Campaign Performance

Set up two agents. One agent, the "Analyst," uses `get_daily_report` to report on overall numbers. A second agent, the "Critic," uses `get_uninstalls_report` to check for corresponding churn. The Analyst might report a spike in installs, but the Critic can immediately challenge that by showing a matching spike in uninstalls, suggesting low-quality traffic. AutoGen facilitates this conversation, letting them arrive at a more nuanced conclusion together.

Assign Roles for Deeper Analysis with AutoGen

Create a "Geo Specialist" agent that only has access to `get_geo_report`. Build a "Partner Manager" agent that only uses `get_partners_report`. When you ask a broad question about performance, they each contribute their specialized view to the conversation. This multi-agent approach, powered by a single MCP server, surfaces connections you'd otherwise miss. The Geo Specialist might point out a dip in a specific country, while the Partner Manager identifies a media source that's underperforming globally.

Build an Automated Investigation Team

Start with a "Monitor" agent that runs `get_account_check` and `get_daily_report`. If it detects an anomaly—like a sudden drop in installs—it can trigger a conversation with an "Investigator" agent. The Investigator agent then takes over the thread. It uses `get_installs_report` and `get_in_app_events_report` to dig into the raw data and find the root cause. This creates a system where agents don't just report problems; they actively work together to solve them.

Setup guide

Set up AppsFlyer (Pull API) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes AppsFlyer (Pull API) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="AppsFlyer (Pull API)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent AppsFlyer (Pull API) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="AppsFlyer (Pull API)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent AppsFlyer (Pull API) data")
    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 AutoGen

When you configure each `AssistantAgent`, you pass a specific list of tools to its constructor. Give your 'analyst' agent the `get_daily_report` tool, and give your 'critic' agent the `get_uninstalls_report` tool. They will only use the functions they are assigned.

Yes, that's a core AutoGen pattern. Your monitoring agent can periodically call a tool like `get_daily_report`. If a metric crosses a threshold, it can initiate a chat with another specialized agent to start an investigation.

A powerful setup is a UserProxyAgent plus two AssistantAgents. One assistant acts as an analyst, pulling aggregate reports with tools like `get_geo_report`. The other acts as a data diver, using `get_installs_report` to get raw data when the analyst needs more detail.

Yes. When you subscribe to this MCP server on Vinkius, you'll provide your AppsFlyer API key. The server then uses your key to pull data from your account. It's your data, made available to your agents.

Only your running agents see the data. The Vinkius platform processes requests for your install reports and in-app event data in a zero-trust, isolated sandbox that is destroyed after each conversation turn. Your raw attribution data is never logged or stored by the MCP server.

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