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

Q: How does LiteLLM (LLM Proxy & Spend Tracking) integrate with Mastra AI workflows?

You attach the tools to your agents, allowing them to call getteaminfo or createmodel during execution. This lets your Mastra AI agents adjust their behavior based on real-time budget data.

Q: Can I use LiteLLM (LLM Proxy & Spend Tracking) to manage Mastra AI credentials?

Yes. You generate keys with generatekey for specific tasks and use deletekey to rotate them. This gives your Mastra AI setup a clean, secure way to handle authentication.

Q: Does LiteLLM (LLM Proxy & Spend Tracking) help Mastra AI with fallback logic?

Absolutely. Your Mastra AI agents can check getmodelinfo to see if a primary model is down and then route to a backup. It makes your agents significantly more reliable in production.

Q: How do I create team-specific budgets?

Run the createteam tool to define a new organizational unit. You then assign keys to that team, and the gateway tracks every cent spent against their specific budget.

Orchestrate complex LLM workflows and automate budget enforcement within your Mastra AI agents.

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 Mastra AI

Create your Vinkius account to connect LiteLLM (LLM Proxy & Spend Tracking) to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated budget enforcement for Mastra AI

Build logic that triggers `get_team_info` before starting any heavy workflow. If a team's budget limit is near, your agent can decide to skip expensive tasks or switch to a smaller model. It turns cost management into a programmatic decision. You stop worrying about runaway bills because the gateway enforces the limits you set.

Dynamic model lifecycle management

Use `delete_model` to prune stale or failing deployments from your Mastra AI agent's available tools. You keep your workflow engine focused on healthy providers only. When you need to add a new model, `create_model` pushes the update to the gateway instantly. Your agents adapt to infrastructure changes without requiring a manual restart.

Scoped access for complex agents

Provision specific API keys for different agent roles using `generate_key`. Each agent gets only the permissions it needs, limiting the blast radius of any potential failure. Verify these permissions anytime with `get_key_info`. You maintain a granular audit trail that tells you exactly which agent used which key and how much it cost.

Setup guide

Set up LiteLLM (LLM Proxy & Spend Tracking) MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All LiteLLM (LLM Proxy & Spend Tracking) tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "litellm-llm-proxy-spend-tracking-mcp-client",
  servers: {
    "litellm-llm-proxy-spend-tracking-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "LiteLLM (LLM Proxy & Spend Tracking) Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to LiteLLM (LLM Proxy & Spend Tracking) tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent LiteLLM (LLM Proxy & Spend Tracking) transactions"
);
console.log(result.text);

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 Mastra AI

You attach the tools to your agents, allowing them to call `get_team_info` or `create_model` during execution. This lets your Mastra AI agents adjust their behavior based on real-time budget data.

Yes. You generate keys with `generate_key` for specific tasks and use `delete_key` to rotate them. This gives your Mastra AI setup a clean, secure way to handle authentication.

Absolutely. Your Mastra AI agents can check `get_model_info` to see if a primary model is down and then route to a backup. It makes your agents significantly more reliable in production.

Run the `create_team` tool to define a new organizational unit. You then assign keys to that team, and the gateway tracks every cent spent against their specific budget.

The server only tracks your LLM API keys and billing metadata. It does not touch your internal agent memory or business logic, ensuring your sensitive data remains within your own environment.

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