How do I find my Umeng App Key and Master Secret?

Log in to the [Umeng portal](https://www.umeng.com/), select your application from the dashboard, and you will find your App Key and App Master Secret in the application settings under 'App Info'.

Does Umeng require different keys for iOS and Android?

Yes. Umeng typically uses separate App Keys for different platforms. Ensure you authorize the correct key depending on which platform's analytics or push notifications you wish to manage.

Can I cancel a push task through the agent?

Yes! Use the `cancel_push` tool with the specific task ID. Your agent will communicate with Umeng to stop the delivery of any pending notification broadcast.

Umeng / 友盟+ MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Umeng / 友盟+
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Umeng / 友盟+ through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Umeng / 友盟+ "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Umeng / 友盟+?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Umeng / 友盟+ MCP Server

Empower your AI agent to orchestrate your mobile growth and engagement with Umeng+ (友盟+), the premier mobile infrastructure provider in China. By connecting Umeng to your agent, you transform complex push notification campaigns and deep analytical auditing into a natural conversation. Your agent can instantly send targeted push messages, retrieve real-time delivery status, monitor user retention trends, and even provide high-level application performance summaries without you ever needing to navigate the comprehensive Umeng portal. Whether you are conducting a growth audit or coordinating a cross-functional marketing blast, your agent acts as a real-time mobile operations assistant, keeping your data accurate and your users engaged.

Pydantic AI validates every Umeng / 友盟+ tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Push Orchestration — Send template-based or custom push notifications and retrieve real-time delivery and click status.
User Growth Auditing — Retrieve detailed metrics for active users, new registrations, and retention across any time period.
Behavioral Analysis — Browse custom event data and session duration statistics to identify user engagement patterns.
Task Management — List recent push tasks and cancel pending operations directly through the agent interface.
Performance Insights — Access high-level application summaries to monitor the health and growth of your mobile ecosystem.

The Umeng / 友盟+ MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Umeng / 友盟+ to Pydantic AI via MCP

Follow these steps to integrate the Umeng / 友盟+ MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Umeng / 友盟+ with type-safe schemas

Why Use Pydantic AI with the Umeng / 友盟+ MCP Server

Pydantic AI provides unique advantages when paired with Umeng / 友盟+ through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Umeng / 友盟+ integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Umeng / 友盟+ connection logic from agent behavior for testable, maintainable code

Umeng / 友盟+ + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Umeng / 友盟+ MCP Server delivers measurable value.

Type-safe data pipelines: query Umeng / 友盟+ with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Umeng / 友盟+ tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Umeng / 友盟+ and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Umeng / 友盟+ responses and write comprehensive agent tests

Umeng / 友盟+ MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Umeng / 友盟+ to Pydantic AI via MCP:

cancel_push

Cancel pending push task

get_active_users

Get active user count

get_app_summary

Get app analytics summary

get_duration_stats

Get session duration stats

get_event_data

Get custom event data

get_new_users

Get new user registrations

get_push_status

Check push task status

get_retention

Get user retention stats

list_push_tasks

List recent push tasks

send_push

Send push notification

Example Prompts for Umeng / 友盟+ in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Umeng / 友盟+ immediately.

"Send a broadcast push saying 'Flash Sale starts now!' to all users."

"Show me the active user metrics for today."

"What is the retention rate for users who joined last Monday?"

Troubleshooting Umeng / 友盟+ MCP Server with Pydantic AI

Common issues when connecting Umeng / 友盟+ to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Umeng / 友盟+ + Pydantic AI FAQ

Common questions about integrating Umeng / 友盟+ MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Umeng / 友盟+ MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.