How to Use the Apideck MCP in Pydantic AI

Q: How do I configure Apideck within a Pydantic AI project?

Run pip install "pydantic-ai-slimmcp" to get the required MCP dependencies. Then, initialize your toolset with MCPToolset("http://...") and pass it to the Agent constructor.

Validate every CRM contact and vault connection schema at runtime using 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 Apideck MCP to Pydantic AI

Create your Vinkius account to connect Apideck 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 Apideck with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe CRM contact lists with Pydantic AI

The `list_crm_contacts` tool returns unified customer records directly to your Pydantic AI agent. The framework validates the incoming JSON payload against your defined schemas at runtime, preventing malformed data from corrupting your application state. If a CRM field changes or returns an unexpected null value, the agent raises a validation error immediately. This loud failure model ensures your production pipelines never process corrupt or hallucinated contact data.

Validate Vault connections and sessions

The `list_vault_connections` and `get_vault_connection` tools retrieve active integration states for your users. Pydantic AI parses these responses into typed models, ensuring your agent always knows the exact status of each connected app. You can also call `create_vault_session` or `delete_vault_connection` to modify these states. Because the schemas are strictly typed, your agent cannot pass invalid parameters to the authentication endpoints.

Proxy raw requests through a verified MCP Server

The `execute_proxy` tool lets your agent send direct API requests to downstream platforms. The Pydantic AI framework intercepts the response, ensuring the returned payload matches the expected structure before passing it to your LLM. This setup works across any model provider, including OpenAI, Anthropic, or local LLMs. Vinkius manages the underlying MCP server, giving your agent a secure, zero-trust connection to the entire integration catalog.

Setup guide

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

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

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

Run `pip install "pydantic-ai-slim[mcp]"` to get the required MCP dependencies. Then, initialize your toolset with `MCPToolset("http://...")` and pass it to the `Agent` constructor.

The framework raises a validation error immediately rather than letting the model guess. This guarantees that tools like `list_crm_contacts` always output clean, structured data.

Yes, it supports both Streamable HTTP and SSE transports. You must run the server externally or point your toolset to your managed Vinkius endpoint.

Yes, Pydantic AI is completely model-agnostic. You can connect your local models to tools like `execute_proxy` as long as they support tool calling.

All vault credentials and session tokens are processed inside an ephemeral, zero-trust V8 sandbox. Vinkius handles the authorization layer, ensuring your Pydantic AI agent never exposes sensitive keys to the LLM or the MCP client.

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