How to Use the Authing MCP in Pydantic AI

Q: How do I configure the Authing MCP Server with Pydantic AI?

Install the slim package with MCP support, then create an MCPToolset pointing to your Vinkius HTTP URL. Pass that object into the toolsets array when initializing your Agent.

Validate every Authing MCP Server response at runtime using Pydantic AI to ensure your identity agents never hallucinate access rules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authing MCP to Pydantic AI

Create your Vinkius account to connect Authing 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 Authing with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe IAM operations

Pydantic AI forces every payload from `get_user` to match your exact Python models before the agent can process it. If the identity provider returns a missing email field, the framework fails loudly so you aren't stuck debugging silent failures. Your code never deals with silent corruption when calling `list_users`. The agent knows exactly what data structure to expect, making it safe to build automated onboarding scripts that depend on precise dictionary keys.

Model-agnostic MCP Server integration

Swapping between LLMs requires zero changes to your identity logic when calling `get_security_settings`. You define the toolset once, and the agent pulls configuration data regardless of which model powers the reasoning engine. Fetching `list_roles` works exactly the same way across different providers. Connecting this MCP Server means your team writes the integration code once and runs it anywhere.

Auditing with strict schemas

Security agents need perfect accuracy when reading `get_audit_logs` to detect breaches. Enforcing runtime checks guarantees the agent cannot invent fake timestamps or user IDs during its analysis phase. Running `list_organizations` returns verified structures that your production database can trust. You build the agent using `toolsets=[toolset]` and let the framework handle the strict type enforcement automatically.

Setup guide

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

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

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

Install the slim package with MCP support, then create an `MCPToolset` pointing to your Vinkius HTTP URL. Pass that object into the `toolsets` array when initializing your Agent.

The framework throws a strict Python exception immediately. Your application catches the error rather than letting the agent continue working with malformed IAM records.

Pydantic AI handles the tool calling logic independently of the LLM provider. You can point the agent at a local Ollama instance and it will still execute `create_user` correctly.

Streamable HTTP is the default for remote connections. Just provide the Vinkius endpoint string and the library manages the network layer.

Every request routes through an isolated V8 environment that vanishes after execution. Your raw security payloads and permission matrices never touch shared memory, keeping your infrastructure completely locked down.

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