How to Use the Lingyi Wanwu MCP in Pydantic AI

Q: How do I initialize the Lingyi Wanwu toolset in Pydantic AI?

Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into the toolsets list when defining your Pydantic AI Agent.

Q: Does Pydantic AI validate the outputs of Lingyi Wanwu tools?

Yes. Every response from tools like chatcompletions is validated against Pydantic schemas at runtime. If the API returns unexpected fields, the framework raises a validation error immediately.

Q: Is the deprecated MCPServerHTTP class still supported?

No. You should use the unified MCPToolset class instead. The older connection classes are deprecated in the latest versions of the Pydantic AI framework.

Q: How is my usage data protected when querying the Lingyi Wanwu MCP?

Usage statistics queried via getusage are transmitted over TLS directly to your client. Vinkius does not store or cache these metrics, ensuring your operational data remains strictly private.

Run type-safe Yi model operations inside Pydantic AI with runtime schema validation and zero silent failures.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lingyi Wanwu MCP to Pydantic AI

Create your Vinkius account to connect Lingyi Wanwu 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 Lingyi Wanwu with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Yi completions against strict Python types

`chat_completions` delivers structured text outputs that Pydantic AI validates against your defined Pydantic models at runtime. This MCP Server prevents corrupted data from entering your database when parsing raw responses from the Yi models, so you won't get silent failures. You can query `list_models` to programmatically verify that the target model supports the specific output schemas you require. This ensures your type-safe pipelines only run against compatible endpoints.

Guard your type-safe workflows against bad data

`check_moderation` runs safety checks on raw inputs before they get parsed into your Pydantic schemas. This tool prevents malicious inputs from causing validation errors or crashing your Pydantic AI agent when handling Yi-specific prompts. By catching policy violations at the edge, you avoid running complex parsing logic on toxic content. This keeps your runtime environment predictable and secure.

Track vector generation and billing metrics

`get_embeddings` produces vector arrays that are strictly typed and validated before they hit your database. Pydantic AI ensures the output dimensions match your schema expectations precisely. To monitor operational costs, `get_usage` retrieves structured billing data. Your agent can validate these metrics against a Pydantic model to trigger alerts if token consumption spikes across this MCP connection.

Setup guide

Set up Lingyi Wanwu 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": {
        "lingyi-wanwu-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Lingyi Wanwu 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 Lingyi Wanwu. 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 Lingyi Wanwu 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 Lingyi Wanwu MCP in Pydantic AI

Use the unified `MCPToolset` class pointing to your Vinkius HTTP endpoint. Pass this toolset instance directly into the `toolsets` list when defining your Pydantic AI Agent.

Yes. Every response from tools like `chat_completions` is validated against Pydantic schemas at runtime. If the API returns unexpected fields, the framework raises a validation error immediately.

The server must run externally, either on Vinkius or your own host. Pydantic AI connects to it via secure Streamable HTTP or SSE transports using your endpoint token.

No. You should use the unified `MCPToolset` class instead. The older connection classes are deprecated in the latest versions of the Pydantic AI framework.

Usage statistics queried via `get_usage` are transmitted over TLS directly to your client. Vinkius does not store or cache these metrics, ensuring your operational data remains strictly private.

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