How to Use the GeTui / 个推 MCP in Pydantic AI

Q: How does the Pydantic AI agent track GeTui / 个推 batch push success?

It calls pushtolist and receives a task ID. It then uses that ID to call getpushstatus, validating the returned delivery metrics against your Pydantic models.

Build type-safe GeTui notification flows with Pydantic AI to guarantee payload structure before any push fires.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GeTui / 个推 MCP to Pydantic AI

Create your Vinkius account to connect GeTui / 个推 to Pydantic AI 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 GeTui / 个推 with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate payloads via MCP Server

The GeTui MCP Server exposes push operations that Pydantic AI validates at runtime. When your agent decides to send an alert, it formats the request for `push_to_single`. If the model hallucinates a field or sends an integer instead of a string, Pydantic catches it immediately and throws a loud validation error. This strict enforcement saves your production campaigns. Batch operations using `push_to_list` require exact array structures, which the framework guarantees before the network request ever leaves your server. You'll never send a malformed push payload again.

Bind aliases with strict types

Managing device connections requires calling `bind_user_alias` to link your internal IDs with GeTui tokens. The agent constructs the mapping request, and Pydantic ensures the alias conforms to your exact schema. If you need to check an existing link, the agent triggers `query_user_alias`. Device state is just as critical. The agent can request `get_cid_status` to see if a phone is online. Because Pydantic AI is model-agnostic, you can swap between Claude and local models without rewriting this validation logic.

Parse Pydantic AI delivery stats

Getting clean analytics means calling `get_daily_push_report` and mapping the response to a strict data model. The agent retrieves the JSON, and the framework ensures every metric aligns with your expected schema. You can also track specific jobs using `get_push_status`. High-level metrics arrive via `get_app_user_stats`. Your agent reads the total registered user count and active device numbers. It can also pull `get_user_tags` to segment the audience, knowing the returned arrays will match the defined Python types perfectly.

Setup guide

Set up GeTui / 个推 MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "getui-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to GeTui / 个推 tools.",
)

result = await agent.run("List recent GeTui / 个推 transactions")
print(result.output)

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 GeTui / 个推. 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 GeTui / 个推 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 GeTui / 个推 MCP in Pydantic AI

Use the MCPToolset class with your HTTP endpoint. You pass this into your Agent constructor under the toolsets argument.

The framework throws a validation error immediately. The agent will not silently process corrupted JSON or hallucinate missing fields.

Pydantic AI is completely model-agnostic. You can connect local inference engines and they will interact with the tools exactly like commercial APIs.

It calls push_to_list and receives a task ID. It then uses that ID to call get_push_status, validating the returned delivery metrics against your Pydantic models.

The server handles user aliases and device tokens natively. Vinkius requires only one endpoint token for access, meaning your raw API secrets never touch the Pydantic runtime environment.

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