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

Q: How do I monitor costs with LiteLLM (LLM Proxy & Spend Tracking) in Claude Desktop?

You use the getuserinfo and getkeyinfo tools. These provide direct access to your current consumption metrics so you can track spend per key or team.

Q: Can I update my model routing via LiteLLM (LLM Proxy & Spend Tracking) using Claude Desktop?

Yes, you can. The createmodel and deletemodel tools allow you to modify your routing paths and fallback configurations dynamically.

Q: Does LiteLLM (LLM Proxy & Spend Tracking) support team isolation in Claude Desktop?

It does. You can use createteam to define organizational units and getteaminfo to check the budget bounds for those specific groups.

Q: Is it possible to revoke access keys securely?

Absolutely. Just trigger the deletekey tool to instantly kill any proxy key that is no longer needed or potentially compromised.

Control model routing and monitor your token spend directly inside the Claude Desktop app using this MCP Server.

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 Claude Desktop

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage your LLM gateway from Claude Desktop

Stop guessing which keys are active or how much your team spent today. You can use `get_key_info` and `get_user_info` to see exact USD consumption without leaving your chat window. It’s about having real-time visibility. When you need to rotate credentials, `generate_key` lets you provision access instantly while `delete_key` cleans up the mess.

Dynamic model routing and fallback configuration

Your AI client needs reliable endpoints to avoid those annoying 500 errors. You can use `create_model` to inject new routes and `get_model_info` to verify that your fallbacks are actually working. If a specific provider goes down, you shift traffic immediately. Use `delete_model` to pull the plug on broken infrastructure before it impacts your production flow.

Team-level isolation for complex projects

Running multiple experiments means you need to keep your budgets separate. Use `create_team` to partition your resources and verify those boundaries with `get_team_info`. It gives you granular control over who uses what. You can map every call back to a specific department or user identity using `create_user` to ensure your spend tracking is accurate.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The LiteLLM (LLM Proxy & Spend Tracking) MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the LiteLLM (LLM Proxy & Spend Tracking) MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under litellm-llm-proxy-spend-tracking-mcp.

json

{
  "mcpServers": {
    "litellm-llm-proxy-spend-tracking-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

You use the `get_user_info` and `get_key_info` tools. These provide direct access to your current consumption metrics so you can track spend per key or team.

Yes, you can. The `create_model` and `delete_model` tools allow you to modify your routing paths and fallback configurations dynamically.

It does. You can use `create_team` to define organizational units and `get_team_info` to check the budget bounds for those specific groups.

Absolutely. Just trigger the `delete_key` tool to instantly kill any proxy key that is no longer needed or potentially compromised.

This server only touches your API key metadata, usage logs, and team configuration settings. It never accesses your actual conversation history or private source code.

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