How to Use the MintMCP MCP in OpenAI Agents SDK

Q: How do I connect MintMCP to the OpenAI Agents SDK?

You instantiate an MCPServerStreamableHttp object with your endpoint and pass it into the mcpservers list of your agent. The SDK handles discovery automatically, mapping your tools into the agent's available action space.

Q: Can I enforce SOC2 policies using MintMCP with OpenAI Agents SDK?

Yes. You fetch your RBAC parameters with mintmcpgettoolpolicy to ensure every agent action aligns with your governance rules. It turns security policy into a verifiable check that runs before code execution.

Q: Does MintMCP support token revocation for OpenAI Agents SDK sessions?

It does. If you detect suspicious activity, trigger mintmcprevokeaccesstoken to immediately kill the session. This severs the connection between your agent and the gateway, preventing further unauthorized access.

Secure your production agent pipeline with MintMCP and the OpenAI Agents SDK to enforce governance before any tool executes.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to OpenAI Agents SDK

Create your Vinkius account to connect MintMCP 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 MintMCP with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pre-flight security validation

Stop dangerous actions before they hit your infrastructure. The `mintmcp_eval_guardrail` tool inspects every request, redacting sensitive data and validating parameters against your security baseline. Your agent gets a clean, safe input stream every time. It keeps the system predictable and prevents unauthorized calls from reaching your backend.

Full audit trails for OpenAI Agents SDK

Track exactly what your agents are doing in real-time. Use `mintmcp_fetch_audit_logs` to pull granular execution history that maps directly to your SOC2 compliance requirements. You won't be left guessing why a specific action occurred. Every tool invocation is logged, timestamped, and stored for your security team to review.

Dynamic virtual server management

Organize your toolsets into logical groups using `mintmcp_list_virtual_servers`. This gateway allows you to abstract your infrastructure, so your agents only see the tools you explicitly approve. Use `mintmcp_get_virtual_server` to verify environment configurations on the fly. It keeps your agent environment clean and prevents scope creep across your deployments.

Setup guide

Set up MintMCP 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 MintMCP tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MintMCP 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="MintMCP Agent",
            instructions="You have access to MintMCP 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 MintMCP. 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 MintMCP 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 MintMCP MCP in OpenAI Agents SDK

You instantiate an `MCPServerStreamableHttp` object with your endpoint and pass it into the `mcp_servers` list of your agent. The SDK handles discovery automatically, mapping your tools into the agent's available action space.

Yes. You fetch your RBAC parameters with `mintmcp_get_tool_policy` to ensure every agent action aligns with your governance rules. It turns security policy into a verifiable check that runs before code execution.

It does. If you detect suspicious activity, trigger `mintmcp_revoke_access_token` to immediately kill the session. This severs the connection between your agent and the gateway, preventing further unauthorized access.

The server acts as a secure proxy that sanitizes all incoming requests. By using `mintmcp_eval_guardrail`, you ensure PII never leaves your controlled environment, keeping your agent interactions private and compliant.

They are. Once you provide the server URL, the SDK introspects the available tools. You can then use `mintmcp_list_available_tools` to confirm which functions are registered and ready for your agents to use.

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