An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect LLM Token Counter to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Keep your prompts within context limits without the guesswork.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 2 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-02

2 capabilities in this set.

Part of 2 available through LLM Token Counter.

  1. 01

    Token count

    This capability calculates character, word, and estimated token counts for any text input.

  2. 02

    Analyze complexity

    This capability evaluates text by looking at linguistic patterns and punctuation diversity.

Real work

What teams actually run

01

Context Window Management

You can calculate exactly how much text fits into a model's limit before sending the request.

02

Prompt Optimization

Use complexity analysis to see how your prompt structure affects the input.

03

Cost Control

Monitor token counts to keep an eye on the volume of data being processed.

04

Template Debugging

Check how much space roles and delimiters take up in your specific chat format.

One connector, every AI

LLM Token Counter works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put LLM Token Counter to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

715ms average. Fast in production.

LLM Token Counter is checked daily against the live service.

Daily averagePeak 971ms
Oct 3Today
Fastest day
548ms
Slowest day
971ms
14-day trend
Improving-23%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 2 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of LLM Token Counter, so you can see the experience inside your AI.

It does not authenticate your account with LLM Token Counter. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

LLM Token Counter Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_zsoth4tZ4xpY6SYfMN3vLiFJZi46jUAy7QtwPENf/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — LLM Token Counter capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "llm-token-counter-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_zsoth4tZ4xpY6SYfMN3vLiFJZi46jUAy7QtwPENf/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up LLM Token Counter in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work LLM Token Counter owners hand off.

This MCP is built for developers and prompt engineers who need to stay within strict model constraints.

  • 01

    LLM Developers

    They use it to manage context windows and prevent errors in model responses.

  • 02

    Prompt Engineers

    They use it to optimize prompt length and manage chat template overhead.

  • 03

    AI Agents

    They use it to self-regulate their own input size before sending requests.

FAQ

Questions LLM Token Counter owners ask.

  • 01

    Which encodings does this MCP support?

    It supports multiple encodings including cl100k_base and o200k_base.

  • 02

    Can I use this with Claude or Cursor?

    Yes, you can connect this MCP to any MCP-compatible client like Claude, Cursor, or Windsurf.

  • 03

    Does it account for chat template overhead?

    Yes, it can calculate the tokens used by structural delimiters in a message.

  • 04

    How does it help with context overflow?

    It provides the exact token counts needed to find the right truncation points for your text.

  • 05

    Is this a hosted MCP?

    Yes, Vinkius hosts and manages the MCP so it is ready to use immediately after connection.

  • 06

    Which LLM tokenizers are supported?

    The server provides exact counts for cl100k_base (GPT-4) and o200k_base (GPT-4o), as well as approximations for Claude and SentencePiece-based models like Llama.

  • 07

    How does the capability handle chat message overhead?

    The calculate_chat_overhead logic accounts for the hidden structural tokens (like role indicators and delimiters) added by API templates to ensure your total token count is accurate.

  • 08

    Can I use this for text truncation?

    Yes, you can use the find_truncation_point capability to determine exactly where to trim your input text to stay within a specific token budget.

Explore

More in Developer Tools

Suggestions

Connect LLM Token Counter to Claude, Cursor, ChatGPT & more