How to Use the LibreChat MCP in OpenAI Agents SDK

Q: How do I configure LibreChat authentication in the OpenAI Agents SDK using MCP?

You run the login tool within your async context manager to fetch active session tokens. Pass these tokens directly into the MCPServerStreamableHttp parameters during initialization. This keeps your credentials secure and eliminates static API key storage in your deployment files.

Q: Can I trace LibreChat agent handoffs inside the OpenAI Agents SDK?

Yes, you can monitor every call to chatcompletions directly through the OpenAI developer dashboard. The SDK automatically logs the payloads sent to your LibreChat Agent IDs. This gives you full visibility into which backend agent handled the prompt.

Q: How does the OpenAI Agents SDK discover LibreChat models?

The SDK calls the listmodels tool at startup when you set the tool caching parameter to true. This retrieves the complete list of configured LibreChat agents and registers them as tools. Your python agents can then route requests to the correct model dynamically.

Q: How does this integration handle my LibreChat credentials?

The login tool handles your username and password strictly within an ephemeral memory space to retrieve refresh tokens. No credentials or chat completion contents are ever stored on the Vinkius platform. All data flows directly between your local python agent and your self-hosted database.

Run your LibreChat agents securely in production using the OpenAI Agents SDK to manage completions and sessions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LibreChat MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Authenticate LibreChat sessions directly

The `login` tool authenticates your OpenAI Agents SDK pipeline directly with your self-hosted LibreChat instance. This tool retrieves the active session tokens and passes them securely to your python runtime. Your OpenAI agent uses these session tokens to maintain persistent connection states across long-running workflows. This setup avoids hardcoding static credentials inside your OpenAI dashboard or agent environment files.

Discover active agents with this MCP Server

The `list_models` tool queries your active LibreChat deployment to fetch available models and custom agent configurations and registers them into your OpenAI Agents SDK schema registry at startup. This auto-discovery mechanism means your OpenAI python agents always know which LibreChat engines are online without manual configuration updates. If you register a new agent in your LibreChat UI, your agent picks it up on the next run using this MCP connection.

Execute completions through OpenAI Agents SDK

The `chat_completions` tool routes raw agent prompts from your OpenAI Agents SDK python code directly to the corresponding LibreChat Agent ID. This allows your OpenAI Agents SDK setup to hand off complex tasks to specialized backend agents. For simpler text generation pipelines, the `open_responses` tool handles quick generation requests with lower latency, allowing the OpenAI Agents SDK to trace these executions on its dashboard.

Setup guide

Set up LibreChat 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 LibreChat tools at runtime.
3

Create your Agent

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

Run the agent

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

You run the `login` tool within your async context manager to fetch active session tokens. Pass these tokens directly into the `MCPServerStreamableHttp` parameters during initialization. This keeps your credentials secure and eliminates static API key storage in your deployment files.

Yes, you can monitor every call to `chat_completions` directly through the OpenAI developer dashboard. The SDK automatically logs the payloads sent to your LibreChat Agent IDs. This gives you full visibility into which backend agent handled the prompt.

The SDK calls the `list_models` tool at startup when you set the tool caching parameter to true. This retrieves the complete list of configured LibreChat agents and registers them as tools. Your python agents can then route requests to the correct model dynamically.

If an ID changes, your python agent will fail to execute the `chat_completions` tool. You should refresh your cached tools list or restart the streamable HTTP server connection to pull the updated models.

The `login` tool handles your username and password strictly within an ephemeral memory space to retrieve refresh tokens. No credentials or chat completion contents are ever stored on the Vinkius platform. All data flows directly between your local python agent and your self-hosted database.

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