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

Q: How do I track spend with LiteLLM (LLM Proxy & Spend Tracking) in Cursor?

You call the getuserinfo tool within your agent session. It returns the total USD consumed, giving you immediate visibility into your usage.

Q: Can Cursor use LiteLLM (LLM Proxy & Spend Tracking) to modify model routes?

Yes. Your agent can call createmodel to update routing endpoints or getmodelinfo to inspect current fallback paths for your requests.

Q: Does LiteLLM (LLM Proxy & Spend Tracking) help manage teams in Cursor?

It does. You can use createteam to define groups and getteaminfo to verify their specific budget limits and model access rights.

Q: Can I delete old keys from within Cursor?

You can. Just tell your agent to invoke deletekey with the target key ID to remove it from your proxy instance.

Inject live cost data and model routing controls directly into your Cursor agent sessions.

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 Cursor

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor model spend inside Cursor

Your agent needs to know the cost of the code it writes. Use `get_user_info` to pull real-time USD consumption data directly into your active chat. This keeps your budget top-of-mind while you build. If you hit a limit, `get_key_info` tells you exactly where your remaining capacity sits.

Real-time model routing for Cursor agents

Don't let dead endpoints kill your momentum. Use `create_model` to add new routes on the fly and `get_model_info` to check if your fallback logic is active. It ensures your agent always has a path forward. When a model becomes obsolete, `delete_model` removes it from your registry instantly.

Provision access keys for your project

You can spin up new credentials without leaving the editor. Use `generate_key` to create scoped access for your microservices and `create_team` to organize them. It keeps your development environment clean. You can even use `delete_key` to prune stale credentials as your architecture evolves.

Setup guide

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

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the LiteLLM (LLM Proxy & Spend Tracking) MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent LiteLLM (LLM Proxy & Spend Tracking) transactions." If the MCP tools are loaded correctly, Cursor will call the LiteLLM (LLM Proxy & Spend Tracking) tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/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 Cursor

You call the `get_user_info` tool within your agent session. It returns the total USD consumed, giving you immediate visibility into your usage.

Yes. Your agent can call `create_model` to update routing endpoints or `get_model_info` to inspect current fallback paths for your requests.

It does. You can use `create_team` to define groups and `get_team_info` to verify their specific budget limits and model access rights.

You can. Just tell your agent to invoke `delete_key` with the target key ID to remove it from your proxy instance.

The server only processes configuration data like team IDs, model routes, and usage totals. It never touches your local files, environment variables, or private 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