How to Use the AI Token Counter MCP in Windsurf

Get exact local token counts directly inside Windsurf Cascade to keep your autonomous agent from hitting context walls.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AI Token Counter MCP to Windsurf

Create your Vinkius account to connect AI Token Counter 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 AI Token Counter with Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pre-Flight Context Checks

The `count_tokens` tool lets Cascade measure your exact payload size before sending a single request to your LLM provider. This prevents your agent from attempting massive multi-file operations that exceed your context window, saving you from failed runs and wasted tokens. Cascade reads your files, plans its sequence, and checks the token count locally. This keeps your autonomous agent running smoothly without manual intervention or sudden truncation errors.

Smart Chunking Decisions

When Cascade processes large directories or long files, it needs to decide whether to split the text or summarize it. This MCP provides the precise metrics needed to make those decisions programmatically. Instead of guessing text length by character count, your agent uses the local tokenization data. This prevents expensive API calls from failing due to oversized payloads.

Budget Defense for Windsurf Agents

Running complex autonomous loops inside Windsurf quickly drains your API budget if left unchecked. By integrating this MCP, you establish a firm boundary for your agent's context consumption. Vinkius runs this tool in a secure sandbox with token optimization that cuts overhead. You get accurate tracking and budget enforcement without exposing your API keys or writing custom parser code.

Setup guide

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

mcp_config.json

{
  "mcpServers": {
    "ai-token-counter-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 GPT Tokenizer. 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 AI Token Counter 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 AI Token Counter MCP in Windsurf

It calculates exact token usage locally before Cascade makes an API call. If the file is too large, Cascade splits the text or summarizes it first. This keeps your agent running without hitting context errors.

Yes, the tokenization logic runs entirely offline on the Vinkius platform. Your Windsurf client connects to the Vinkius endpoint, which handles the calculations in a fast V8 sandbox. This avoids sending your raw data to external LLM providers just to count tokens.

You can edit your local config file or use the Windsurf settings UI under the Cascade section. Add the Vinkius endpoint URL and your access token. Cascade automatically discovers the tools and starts using them in its planning loops.

Yes, it supports standard tokenization formats used by major model providers. It uses the exact cl100k_base encoding rules to match the output of your chosen AI client. This ensures your counts match what the providers actually bill you for.

All text strings sent for token counting pass through a zero-trust proxy and execute in a secure V8 isolate sandbox. Vinkius never writes your raw text to disk, and the data is wiped immediately after the count is returned. You get a signed, tamper-proof audit trail of the execution without risking data exposure.

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