How to Use the LiteLLM (LLM Proxy & Spend Tracking) MCP in AutoGen

Q: Can AutoGen agents manage API keys using LiteLLM (LLM Proxy & Spend Tracking)?

Yes. A security agent in your AutoGen group can invoke generatekey via this MCP Server to create isolated keys or deletekey to revoke them during multi-agent workflows.

Q: How do AutoGen agents negotiate model routing using LiteLLM (LLM Proxy & Spend Tracking)?

Your agents can query getmodelinfo to inspect routing paths and fallback options. They can then debate the trade-offs of speed and cost before sending queries through the gateway.

Q: Can I monitor multi-agent team budgets in AutoGen using LiteLLM (LLM Proxy & Spend Tracking)?

Yes. A supervisor agent can call getteaminfo or getuserinfo to track USD consumption and ensure no individual agent or team exceeds their budget.

Q: How do I add new routing endpoints dynamically in a conversation?

An agent can run the createmodel tool to inject a new endpoint, such as a Bedrock Llama 4 route, making it immediately available to all other agents in the conversation.

Let your AutoGen agents debate, allocate, and manage LiteLLM gateway budgets and model keys dynamically.

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 AutoGen

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent gateway resource allocation

Run a fully automated multi-agent system where a budget manager agent debates a developer agent over this MCP Server. The budget manager checks `get_key_info` and decides whether to approve a new project key. If approved, the provisioning agent calls `generate_key` to issue the credential. When a project is finished, a security agent can call `delete_key` to revoke access. This multi-agent consensus model removes human bottlenecks from your API key lifecycle.

Collaborative fallback selection in this MCP Server

Let your AutoGen agents negotiate which model to use based on live performance. A performance agent queries `get_model_info` to analyze routing paths, while a cost agent checks `get_user_info` to monitor spending. They negotiate the best balance of speed and cost before running a heavy task. If they decide a new endpoint is needed, they call `create_model` to inject it into the gateway.

Automated team boundary enforcement

Prevent rogue agents from draining your main API budget using this MCP Server. A supervisor agent can run `get_team_info` to monitor cost limits across different divisions. If a team agent exceeds its limit, the supervisor calls `create_team` to adjust the threshold. You can also register new users dynamically by calling `create_user`. This ensures that every agent's actions are mapped to a clear identity and budget limit.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) 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 LiteLLM (LLM Proxy & Spend Tracking) 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="LiteLLM (LLM Proxy & Spend Tracking)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent LiteLLM (LLM Proxy & Spend Tracking) 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="LiteLLM (LLM Proxy & Spend Tracking)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent LiteLLM (LLM Proxy & Spend Tracking) 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 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 AutoGen

Yes. A security agent in your AutoGen group can invoke `generate_key` via this MCP Server to create isolated keys or `delete_key` to revoke them during multi-agent workflows.

Your agents can query `get_model_info` to inspect routing paths and fallback options. They can then debate the trade-offs of speed and cost before sending queries through the gateway.

Yes. A supervisor agent can call `get_team_info` or `get_user_info` to track USD consumption and ensure no individual agent or team exceeds their budget.

An agent can run the `create_model` tool to inject a new endpoint, such as a Bedrock Llama 4 route, making it immediately available to all other agents in the conversation.

All routing configurations, team API keys, and spending logs are processed inside this MCP Server's zero-trust V8 isolate sandbox. The server runs ephemerally, ensuring that no sensitive credentials or logs are written to persistent storage.

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