How to Use the Apidog MCP in Pydantic AI

Q: Is the old MCPServerHTTP class still supported?

No, that class is deprecated. You should use the unified MCPToolset constructor to connect your agent to the hosted server.

Stop silent API failures by validating Apidog schemas at runtime with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apidog MCP to Pydantic AI

Create your Vinkius account to connect Apidog 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 Apidog with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stop silent failures in Pydantic AI

`get_endpoint` pulls live endpoint schemas directly from your Apidog projects. Pydantic AI uses this data to validate model outputs at runtime, throwing explicit errors if things drift. Instead of letting your agent hallucinate parameters, the system catches structural mismatches instantly. You get guaranteed type safety before any HTTP call is made.

Inspect project structures programmatically

`list_projects` finds your active API designs inside your Apidog organization. Your agent can scan these projects to locate the exact service it needs to interact with. Follow this up with `list_endpoints` to discover the active routes. The framework validates the returned lists against Pydantic models, ensuring your agent never processes corrupt metadata.

Export OpenAPI specs for dynamic model generation

`export_openapi` downloads the full OpenAPI 3.0 specification file as a clean JSON object. Your application can parse this spec to generate Pydantic models on the fly. This prevents manual coding of data transfer objects. Your codebase syncs with your API design workspace, allowing your MCP agent to adapt to upstream changes.

Setup guide

Set up Apidog 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": {
        "apidog-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

The framework validates every MCP response against its internal models. If the server returns a malformed schema, Pydantic AI raises a validation error immediately.

It supports both Streamable HTTP and SSE transports. You initialize the connection using the `MCPToolset` class pointing to your Vinkius hosted URL.

Yes, Pydantic AI is model-agnostic. You can bind these tools to local models or commercial APIs while maintaining strict runtime validation.

No, that class is deprecated. You should use the unified `MCPToolset` constructor to connect your agent to the hosted server.

All transactions occur in an isolated, ephemeral V8 sandbox. Your credentials and OpenAPI specifications are never cached or logged by Vinkius.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.