How to Use the Lit Protocol (Decentralized Access Control) MCP in Pydantic AI

Q: How do I register Lit Protocol (Decentralized Access Control) in Pydantic AI?

You instantiate MCPToolset with the server's HTTP URL and pass it to the Agent constructor. Pydantic AI automatically inspects the 20 available tools and generates strict validation schemas for each of them.

Q: Can I run Lit Protocol (Decentralized Access Control) actions asynchronously in Pydantic AI?

Yes, the MCPToolset supports asynchronous execution. Your agent can call executelitaction or addpkptogroup concurrently without blocking the main Python event loop.

Q: How do I manage group permissions with this MCP Server?

You use addgroup to create a permission boundary, then add PKPs using addpkptogroup. The agent can verify the active groups by calling listgroups to ensure proper access control.

Q: How does this server secure my payment intents and billing data?

The MCP Server handles payment data through Stripe via createpaymentintent and confirmpayment. This sensitive financial data is processed entirely within Vinkius's zero-trust sandboxed environment, keeping your credit cards and balances safe from external exposure.

Validate decentralized access control workflows in Pydantic AI with Lit Protocol (Decentralized Access Control).

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lit Protocol (Decentralized Access Control) MCP to Pydantic AI

Create your Vinkius account to connect Lit Protocol (Decentralized Access Control) 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 Lit Protocol (Decentralized Access Control) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe wallet creation with Pydantic AI

This MCP server uses `create_wallet` to generate Programmable Key Pairs and returns the public key structured as a validated Python object. Pydantic AI ensures that your agent receives exactly the expected data types, preventing silent failures during execution. The agent checks the wallet's status by executing `list_wallets`. If the Lit network returns malformed data, Pydantic AI throws a validation error immediately rather than letting the agent proceed with bad data.

Execute verified Lit Actions via MCP Server

The `execute_lit_action` tool runs your decentralized code inside a secure TEE and returns the cryptographic signature. This MCP Server integrates with Pydantic AI to parse and validate the signature payload before your agent uses it. Your agent manages these actions by registering them with `add_action` or grouping them via `add_action_to_group`. Every step of the cryptographic pipeline is strictly typed, ensuring absolute runtime correctness.

Track your billing balance with strict validation

The `get_billing_balance` tool retrieves your current credit balance as a validated decimal value. Pydantic AI checks this value against your runtime constraints to ensure the agent has enough funds before initiating a transaction. To manage access, your agent can call `add_usage_api_key` and inspect the resulting key metadata. If you need to revoke access, the agent executes `remove_usage_api_key` to clean up the environment safely.

Setup guide

Set up Lit Protocol (Decentralized Access Control) 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": {
        "lit-protocol-decentralized-access-control-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Lit Protocol (Decentralized Access Control) 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 Lit Protocol. 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 Lit Protocol (Decentralized Access Control) 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 Lit Protocol (Decentralized Access Control) MCP in Pydantic AI

You instantiate `MCPToolset` with the server's HTTP URL and pass it to the `Agent` constructor. Pydantic AI automatically inspects the 20 available tools and generates strict validation schemas for each of them.

Pydantic AI will instantly raise a validation error. If a tool like `list_wallets` or `get_billing_balance` returns an unexpected payload, the framework halts execution instead of letting the agent hallucinate a response.

Yes, the `MCPToolset` supports asynchronous execution. Your agent can call `execute_lit_action` or `add_pkp_to_group` concurrently without blocking the main Python event loop.

You use `add_group` to create a permission boundary, then add PKPs using `add_pkp_to_group`. The agent can verify the active groups by calling `list_groups` to ensure proper access control.

The MCP Server handles payment data through Stripe via `create_payment_intent` and `confirm_payment`. This sensitive financial data is processed entirely within Vinkius's zero-trust sandboxed environment, keeping your credit cards and balances safe from external exposure.

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