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

Q: How do I add LiteLLM (LLM Proxy & Spend Tracking) to Claude Code?

Run claude mcp add followed by the server URL. Claude Code will then recognize the tools for your terminal sessions.

Q: Can I automate LiteLLM (LLM Proxy & Spend Tracking) tasks in Claude Code?

You can. Since Claude Code is headless, you can script generatekey or deletemodel calls into your existing CI/CD workflows.

Q: How do I check my spend in Claude Code using LiteLLM (LLM Proxy & Spend Tracking)?

Call getuserinfo with a user ID. The server will return the total USD consumed, which you can then log to your terminal.

Q: Is there a way to verify my model fallbacks in the terminal?

Yes. Use getmodelinfo to see the complete path. It prints the active routing rules directly to your shell output.

Manage your proxy infrastructure from the terminal. Claude Code and this MCP Server handle keys, spend, and routing natively.

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 Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless gateway administration

Automate your infrastructure management with CLI-based tool calls. Use `generate_key` and `delete_key` inside your scripts to manage access dynamically. Pipe the output to other utilities to monitor your environment. You get full control over your proxy without ever opening a GUI.

Spend tracking for DevOps

Monitor your LLM budget directly from the shell. Call `get_user_info` to pull usage data and feed it into your cost-reporting pipelines. Use `create_team` to organize your infrastructure. It ensures every dollar spent is mapped to the correct internal division.

Dynamic routing for CI/CD

Inject or remove model endpoints automatically during your deployment process. Use `create_model` to update your routing logic based on current availability. Verify your setup with `get_model_info`. It returns the exact fallback path, ensuring your pipelines don't break when a provider goes down.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see litellm-llm-proxy-spend-tracking-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest LiteLLM (LLM Proxy & Spend Tracking) transactions." It will automatically discover and invoke the available LiteLLM (LLM Proxy & Spend Tracking) tools.

Terminal

claude mcp add --transport http litellm-llm-proxy-spend-tracking-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the LiteLLM (LLM Proxy & Spend Tracking) MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "litellm-llm-proxy-spend-tracking-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add` followed by the server URL. Claude Code will then recognize the tools for your terminal sessions.

You can. Since Claude Code is headless, you can script `generate_key` or `delete_model` calls into your existing CI/CD workflows.

Call `get_user_info` with a user ID. The server will return the total USD consumed, which you can then log to your terminal.

Yes. Use `get_model_info` to see the complete path. It prints the active routing rules directly to your shell output.

The server uses isolated environment variables for your keys. It only logs metadata like USD spend and routing paths, keeping your secrets out of the logs.

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