An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Prompt Token Analyzer 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. Control your token spend and optimize prompt context.

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 · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Prompt Token Analyzer.

  1. 01

    Analyze prompt sections

    This capability performs a full breakdown of how many tokens each part of your prompt consumes relative to your budget.

  2. 02

    Find outlier sections

    This capability identifies specific sections that are significantly larger or smaller than the average size of your other sections.

  3. 03

    Get section stats

    This capability provides high-level summary statistics regarding the composition of your prompt.

Real work

What teams actually run

01

Cost Control

You can set a token budget and check if your prompt stays under that limit before sending it to your AI client.

02

Prompt Optimization

You can find which parts of your instructions are taking up too much space and trim them down.

03

Context Management

You can ensure your complex prompts do not exceed the maximum context window of your agent.

04

Structural Auditing

You can use outlier detection to see if a specific data block is overwhelming your system instructions.

One connector, every AI

Prompt Token Analyzer 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 Prompt Token Analyzer 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

843ms average. Fast in production.

Prompt Token Analyzer is checked daily against the live service.

Daily averagePeak 1406ms
Oct 3Today
Fastest day
594ms
Slowest day
1406ms
14-day trend
Improving-31%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 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 Prompt Token Analyzer, so you can see the experience inside your AI.

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

Prompt Token Analyzer Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_ZgehUUQz5CT25DulG0SEu9HRgQOCIVnjLGCggzWK/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 — Prompt Token Analyzer capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "prompt-token-analyzer-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ZgehUUQz5CT25DulG0SEu9HRgQOCIVnjLGCggzWK/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 Prompt Token Analyzer in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Prompt Token Analyzer owners hand off.

This is built for developers and prompt engineers who need to manage context windows and costs.

  • 01

    Prompt Engineers

    They use it to refine instructions and ensure they fit within model limits.

  • 02

    AI Developers

    They use it to predict and control the cost of LLM workflows.

  • 03

    LLM Researchers

    They use it to analyze how different prompt structures impact token usage.

FAQ

Questions Prompt Token Analyzer owners ask.

  • 01

    How does this MCP calculate tokens?

    It uses a deterministic ratio of 4 characters per token to estimate consumption.

  • 02

    Which AI clients can use this MCP?

    It works with any MCP-compatible client including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I use this to find large parts of my prompt?

    Yes, the find_outlier_sections capability specifically identifies sections that are significantly larger or smaller than the average.

  • 04

    Do I need to host this myself?

    No, Vinkius hosts and manages the MCP for you so it is ready to use immediately.

  • 05

    Is this useful for controlling LLM costs?

    Yes, by monitoring token budgets and identifying bloated sections, you can better manage your spending.

  • 06

    How is the token count calculated?

    The server uses a deterministic proxy where the token count is the total number of characters in a section divided by four.

  • 07

    Can I identify which parts of my prompt are too large?

    Yes, you can use the find_outlier_sections capability to identify sections that are significantly larger or smaller than the average size.

  • 08

    What happens if I exceed my token budget?

    The analyze_prompt_sections capability will return a negative budget remaining value and set the budget overrun flag to true.

Explore

More in Developer Tools

Suggestions

Connect Prompt Token Analyzer to Claude, Cursor, ChatGPT & more