How to Use the Lit Protocol (Decentralized Access Control) MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK discover Lit Protocol (Decentralized Access Control) tools?

Your Python setup uses MCPServerStreamableHttp to automatically register all 20 tools. The OpenAI Agents SDK discovers tools like executelitaction and createwallet during initialization, making them immediately available to your agent.

Q: How do I manage payment credits for Lit Protocol (Decentralized Access Control) using OpenAI Agents SDK?

The agent uses createpaymentintent and confirmpayment to top up your balance. It monitors the remaining credits using getbillingbalance to ensure your automated workflows never run out of execution power.

Q: What is the best way to handle API keys with this MCP Server?

Use addusageapikey to generate scoped keys for your agent. You can update their access permissions using updateusageapikey or revoke them entirely via removeusageapikey when they are no longer needed.

Build secure, self-custodial agent workflows using Lit Protocol (Decentralized Access Control) with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Lit Protocol (Decentralized Access Control) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision PKPs directly from OpenAI Agents SDK

This MCP server exposes the `create_wallet` tool to let your OpenAI Agents SDK instantiate Programmable Key Pairs (PKPs) on the fly. When your python agent requests a new wallet, the Lit network generates a distributed key share without exposing the private key to the host environment. The agent checks the setup using `list_wallets` to track active keys before triggering any on-chain actions. This setup relies on Vinkius ephemerality, ensuring no keys are cached or exposed during execution.

Control credential boundaries with PKP groups

This MCP toolset uses `add_group` and `add_pkp_to_group` to segment your decentralized access permissions. Your OpenAI agent dynamically assigns wallets to specific authorization levels as your workflow scales. If an agent's role changes, the SDK triggers `remove_pkp_from_group` to revoke its access instantly. The OpenAI guardrails validate these group updates before they commit, preventing unauthorized privilege escalation.

Execute secure Lit Actions in TEEs

The `execute_lit_action` tool runs your raw code or IPFS CIDs inside decentralized Trusted Execution Environments. This MCP Server ensures that your OpenAI Agents SDK triggers cryptographic signatures without ever holding the underlying keys. You manage the execution logic by registering files using `add_action` and confirming the payment using `create_payment_intent`. The agent monitors the billing balance with `get_billing_balance` to avoid execution failures.

Setup guide

Set up Lit Protocol (Decentralized Access Control) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Lit Protocol (Decentralized Access Control) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Lit Protocol (Decentralized Access Control) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Lit Protocol (Decentralized Access Control) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Lit Protocol (Decentralized Access Control) Agent",
            instructions="You have access to Lit Protocol (Decentralized Access Control) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your Python setup uses `MCPServerStreamableHttp` to automatically register all 20 tools. The OpenAI Agents SDK discovers tools like `execute_lit_action` and `create_wallet` during initialization, making them immediately available to your agent.

Yes, you can configure guardrails inside your OpenAI Agents SDK constructor. This prevents your agent from calling sensitive tools like `remove_group` or `update_usage_api_key` unless safety parameters match.

The agent uses `create_payment_intent` and `confirm_payment` to top up your balance. It monitors the remaining credits using `get_billing_balance` to ensure your automated workflows never run out of execution power.

Use `add_usage_api_key` to generate scoped keys for your agent. You can update their access permissions using `update_usage_api_key` or revoke them entirely via `remove_usage_api_key` when they are no longer needed.

This MCP Server runs inside Vinkius's zero-trust V8 isolate sandbox. Your PKP metadata and API keys are never stored on disk, and the actual threshold key shares remain distributed across the Lit node network, completely invisible to the OpenAI agent.

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