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

Q: Can Windsurf manage my keys using LiteLLM (LLM Proxy & Spend Tracking)?

Yes. You can use the generatekey and deletekey tools to provision or revoke access directly from your chat window.

Q: Does LiteLLM (LLM Proxy & Spend Tracking) track my Windsurf spend?

It does. You can use getuserinfo to see the total USD consumed by specific user identities managed through the proxy.

Q: What happens if a model fails during a Windsurf task?

The server uses getmodelinfo to verify your fallback paths. If the primary endpoint is failing, the proxy redirects traffic to your configured backup.

Stop guessing your LLM costs. Let Windsurf and this MCP Server manage your proxy keys and model fallbacks automatically.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated proxy key management

Cascade needs to move fast without manual key generation. Use `generate_key` to spin up credentials for your microservices while keeping them siloed. Keep your budget in check by using `get_key_info` to audit exactly what a key is allowed to spend before a request even leaves your IDE.

Dynamic model routing control

When an endpoint goes down, you don't want to dig through config files. Use `create_model` to inject fresh routing endpoints directly into your environment. Verify your failover logic by calling `get_model_info` to inspect the fallback path from your primary provider to your backup.

Granular team cost tracking

Stop guessing which department burned through the budget. Call `create_team` to isolate costs by division and enforce strict usage limits. Use `get_team_info` to pull the current logic bounds for any team. It tells you exactly where the money is going without needing to check a separate dashboard.

Setup guide

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

Prerequisites

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

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my LiteLLM (LLM Proxy & Spend Tracking) payment history." If connected, Cascade will call the LiteLLM (LLM Proxy & Spend Tracking) tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your MCP settings in Windsurf and add the server configuration. Once connected, Cascade will index the tools and handle the rest.

Yes. You can use the `generate_key` and `delete_key` tools to provision or revoke access directly from your chat window.

It does. You can use `get_user_info` to see the total USD consumed by specific user identities managed through the proxy.

The server uses `get_model_info` to verify your fallback paths. If the primary endpoint is failing, the proxy redirects traffic to your configured backup.

Your API keys and cost metrics stay within your infrastructure. The server only touches metadata and routing logic, never your actual prompt content.

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