How to Use the LiteLLM (LLM Proxy & Spend Tracking) MCP in OpenAI Agents SDK

Manage your MCP Server and enforce spend limits directly inside your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiteLLM (LLM Proxy & Spend Tracking) MCP to OpenAI Agents SDK

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Your MCP Server via OpenAI Agents SDK

Your production agents can spin up or tear down credentials on demand. By exposing `generate_key` and `delete_key` directly to OpenAI Agents SDK, your system manages access without human intervention. This prevents key sprawl and keeps your multi-agent architecture secure. This MCP Server allows the SDK to auto-discover these tools during startup. When an agent detects a new microservice spinning up, it calls the proxy server to provision a key with exact budget caps, then passes that key to the next specialized agent.

Dynamic Model Fallbacks for Reliable Runs

Stop letting API outages break your production runs. When a model goes down, the agent checks fallback paths via `get_model_info` and updates routes using `create_model` or `delete_model` to keep the pipeline alive. This MCP Server allows your OpenAI Agents SDK setup to dynamically adapt to upstream provider failures. Instead of hardcoding backup engines, your agent queries current routes and swaps endpoints on the fly.

Real-Time Spend Auditing and Team Budgets

Keep your multi-agent deployments from burning through your budget. Your agent inspects team limits using `get_team_info` and monitors user consumption via `get_user_info` before spinning up expensive reasoning tasks. If a team approaches its hard limit, the agent triggers a handoff or pauses execution. By checking `get_key_info` first, you prevent surprise bills on your OpenAI dashboard.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LiteLLM (LLM Proxy & Spend Tracking) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LiteLLM (LLM Proxy & Spend Tracking) 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="LiteLLM (LLM Proxy & Spend Tracking) Agent",
            instructions="You have access to LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM. 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 LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) MCP in OpenAI Agents SDK

Install openai-agents and initialize the server using MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this instance in the mcp_servers list when creating your Agent. The SDK automatically registers all ten gateway management tools.

Yes, you can configure guardrails in the SDK to validate parameters before the agent calls `generate_key`. This ensures the agent never creates a key with a budget exceeding your pre-approved limit.

When one agent finishes a task, it can pass the tracked credentials retrieved via `get_key_info` to the next agent. This keeps the entire execution chain under a single, traceable billing profile.

Yes, set cacheToolsList=True in your configuration to prevent the SDK from querying the server on every turn. This reduces latency while keeping the gateway tools ready for action.

All proxy credentials, team budgets, and routing rules remain inside your isolated Vinkius V8 sandbox. The server only processes management requests like `get_key_info` and never exposes your raw provider keys to external networks.

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