How to Use the Anthropic MCP in Windsurf

Q: How does Windsurf use the Anthropic MCP Server to save on API costs?

Cascade triggers createbatch for non-urgent tasks like bulk testing or document translation. This cuts your token bill in half. Cascade handles the polling and pulls the results right back into your active editor.

Q: Can Windsurf automatically switch Claude models if I hit a rate limit?

Yes, Cascade uses checkratelimits alongside listmodels to check your current tier status. If you are about to hit a wall, Cascade can switch its backend model to keep your development momentum going without manual intervention.

Q: Can I stop a running batch job from the editor?

You can tell Cascade to run cancelbatch with the specific ID. It stops the remote processing immediately so you don't get billed for unfinished runs.

Run cheaper, smarter Claude workflows inside Windsurf by letting Cascade run batches and monitor your API limits on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Anthropic MCP to Windsurf

Create your Vinkius account to connect Anthropic 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 Anthropic with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run batch processing runs without touching a script

This MCP Server lets Cascade use `create_batch` and `get_batch_results` to run massive asynchronous runs directly inside your Windsurf workspace. Instead of writing custom python scripts to parse batch files, Cascade builds the batch payload, sends it off, and checks back later. You save fifty percent on token costs without writing boilerplate code. Cascade waits for the run to finish, grabs the output, and immediately starts refactoring your local files based on those cheaper Claude responses.

Live rate limit tracking inside Windsurf

Cascade uses `check_rate_limits` to keep your workspace from hitting hard API blocks during heavy agentic coding sessions. When Cascade plans a long sequence of file edits, it checks your remaining quota first to prevent mid-task failures. If you are close to your tier cap, Cascade automatically throttles its requests or suggests switching models. You never get stuck with half-written files because of a sudden 429 error from the Anthropic API.

Cost estimation before running heavy agent runs

This MCP Server exposes `estimate_cost` and `get_model_specs` so Cascade can calculate the financial impact of your prompt chains. Before Cascade executes a twenty-step refactoring plan, it analyzes your codebase size and predicts the exact token spend. This gives you a clear picture of your budget before Cascade starts writing code. You can swap to a faster, cheaper model variant if the estimate for Claude 3.5 Sonnet looks too high for a quick test run.

Setup guide

Set up Anthropic 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 Anthropic 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 Anthropic payment history." If connected, Cascade will call the Anthropic tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "anthropic-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 Anthropic. 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 Anthropic 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 Anthropic MCP in Windsurf

Cascade triggers `create_batch` for non-urgent tasks like bulk testing or document translation. This cuts your token bill in half. Cascade handles the polling and pulls the results right back into your active editor.

Yes, Cascade uses `check_rate_limits` alongside `list_models` to check your current tier status. If you are about to hit a wall, Cascade can switch its backend model to keep your development momentum going without manual intervention.

No manual mapping is required. Once you add the server endpoint to your Windsurf configuration, Cascade automatically discovers tools like `create_message` and starts using them in its planning loops through the MCP Server.

You can tell Cascade to run `cancel_batch` with the specific ID. It stops the remote processing immediately so you don't get billed for unfinished runs.

Your credentials and raw prompt data never touch third-party servers. Vinkius runs the server in an isolated sandbox, passing your messages directly to the official Anthropic API endpoint.

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