How to Use the LibreChat MCP in AutoGen

Q: How do AutoGen agents authenticate with LibreChat?

Your primary AutoGen assistant agent calls the login tool at the start of the session. The returned tokens are then shared across your agent group to authorize chatcompletions on your LibreChat instance.

Q: Can AutoGen agents dynamically select LibreChat models during a conversation?

Yes. An AutoGen agent can call listmodels to see what's active, then pass the target model ID to another agent who executes chatcompletions on your LibreChat server.

Let your AutoGen agents debate and coordinate using live LibreChat model configurations.

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 AutoGen

Create your Vinkius account to connect LibreChat to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent debate using the LibreChat MCP Server

Build complex AutoGen conversations where different agents use different LLMs. One AutoGen agent can call `list_models` to find a specialized LibreChat model, while another uses a generalist one. They can debate the output of a prompt, calling `chat_completions` to refine the answer until your AutoGen agents reach a consensus, combining their strengths.

Consensus-driven completions

Get raw, unformatted model outputs for your AutoGen agents to analyze. By calling `open_responses`, your critic agent can review raw text from LibreChat before your main agent formats the final response. This workflow prevents formatting errors from breaking your AutoGen loops. The critic flags issues, and the writer calls `chat_completions` on your LibreChat instance to patch the code.

Automated session management

Keep your AutoGen multi-agent loops running without manual token refreshes. AutoGen agents can trigger the `login` tool to refresh their LibreChat session state whenever an authentication error is detected. This self-healing mechanism ensures long-running conversations don't fail halfway through because of expired credentials, keeping your autonomous AutoGen pipelines active.

Setup guide

Set up LibreChat MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes LibreChat tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="LibreChat_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LibreChat data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="LibreChat_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LibreChat data")
    print(result.messages[-1].content)

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 AutoGen

Your primary AutoGen assistant agent calls the `login` tool at the start of the session. The returned tokens are then shared across your agent group to authorize `chat_completions` on your LibreChat instance.

Yes. An AutoGen agent can call `list_models` to see what's active, then pass the target model ID to another agent who executes `chat_completions` on your LibreChat server.

This server gives your AutoGen agents direct access to your custom LibreChat setups, including `open_responses` for raw text generation and custom agents configured on your instance.

Yes. The MCP Server integrates with AutoGen's StreamableHttpServerParams, allowing you to stream tool outputs like `chat_completions` in real time during agent debates.

The message payloads and agent configurations processed during `chat_completions` go directly to your configured instance. Vinkius processes this data in a secure, ephemeral sandbox that is wiped immediately after execution.

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