How to Use the Deterministic JWT Inspector MCP in Pydantic AI

Q: How do I add the Deterministic JWT Inspector to Pydantic AI?

Use the unified MCPToolset class with your Vinkius HTTP endpoint URL. Pass the resulting toolset directly into your Agent definition. Avoid the deprecated MCPServerHTTP method.

Decode JWTs with strict type safety in Pydantic AI without setting up complex cryptographic verification pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deterministic JWT Inspector MCP to Pydantic AI

Create your Vinkius account to connect Deterministic JWT Inspector 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 Deterministic JWT Inspector with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Payload Validation

The `inspect_jwt` tool decodes JSON Web Token structures into raw JSON, exposing the header and payload claims. Pydantic AI takes this output and validates it against your predefined models, failing loudly if the token structure is malformed. Let's get one thing straight—silent failures in auth debugging will ruin your day. By pushing the raw extraction to an MCP server, your agent gets clean data to validate. If the issuer field is missing, Pydantic catches it immediately.

Deterministic JWT Inspector MCP Server

The `inspect_jwt` tool reads the timestamp claims and calculates exactly how many seconds remain until token expiration. Your agent receives this as structured data, not a vague text summary. You need exact numbers, not guesses. The MCP server does the math and returns the relative expiry time, letting your model-agnostic agent trigger strict timeout protocols based on actual token data.

Pure Decoding Mechanics

The `inspect_jwt` tool strips away the signature verification process entirely, focusing purely on base64url parsing. It requires zero configuration, zero public keys, and zero external dependencies. Developers waste hours trying to inspect tokens in environments without access to the JWKS endpoint. This tool solves that annoyance. You hand it a string, and it hands back the internal structure, letting your agent continue its diagnostic work without interruption.

Setup guide

Set up Deterministic JWT Inspector 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": {
        "deterministic-jwt-inspector-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Deterministic JWT Inspector 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 jwt-inspector. 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 Deterministic JWT Inspector 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 Deterministic JWT Inspector MCP in Pydantic AI

Use the unified `MCPToolset` class with your Vinkius HTTP endpoint URL. Pass the resulting toolset directly into your `Agent` definition. Avoid the deprecated `MCPServerHTTP` method.

Online debuggers require manual pasting and risk exposing sensitive tokens to third-party sites. This MCP server automates the process securely within your agent's workflow, keeping the data local to your execution environment.

No, it intentionally ignores them. The tool is designed strictly for extracting data from the header and payload. It will successfully decode a token even if the signature is completely broken.

The tool will fail to parse the base64url segments and return an error. Pydantic AI will catch this failure and alert the agent that the provided string is not a valid token structure.

Your raw JWT strings are decoded inside a completely isolated V8 sandbox. Vinkius tears down the environment immediately after extraction, ensuring no payload claims or headers ever hit a disk or log file.

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