Code Block Token Analyzer Connector for AI agents.
3 live capabilities
Calculate token density and code ratios in technical documents
Waiting for input…
Why people use Code Block Token Analyzer
Solve context window issues with Code Block Token Analyzer
This MCP changes that by giving you a mathematical way to see the density of your input. Instead of guessing, you get a clear picture of the code-to-text ratio. You'll know exactly how much of your prompt is logic and how much is explanation, allowing you to trim the fat before you ever hit send.
What Vinkius changes
You get a mathematical breakdown of how much context your code-heavy files will actually consume.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,400+ Connectors
- Real-world use case 01
Managing massive refactoring tasks
A developer needs to refactor a 500-line file and uses the MCP to see if the code-to-text ratio will blow out their context window.
- Real-world use case 02
Validating technical documentation
A writer wants to make sure their Markdown files have valid triple-backtick blocks so their agent doesn't ignore the code snippets.
- Real-world use case 03
Optimizing prompt efficiency
A prompt engineer uses the density summary to decide if they should strip out comments to save tokens before sending a request.
Complete set · 3capabilities
The complete Code Block Token Analyzer capability set.
These are the exact actions your AI can choose when you ask it to work with Code Block Token Analyzer.
01—03
3 capabilities in this set.
Part of 3 available through Code Block Token Analyzer.
- 01 Capability
Validate code block format
Checks if your text contains valid triple-backtick code blocks. It ensures your agent can actually find and read the code you've provided.
- 02 Capability
Analyze text density
Provides a full breakdown of code blocks, character counts, and token ratios. It's the deep dive for understanding text composition.
- 03 Capability
Get token metrics summary
Returns a high-level summary of token distribution. Use this for a quick check on whether a file is code-heavy.
Set up in minutes
One URL. Then ask Code Block Token Analyzer to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Code Block Token Analyzer from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Code Block Token Analyzer, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Code Block Token Analyzer for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Code Block Token Analyzer URL.
- Step 03
Save and start
Save the connection and enable Code Block Token Analyzer in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"code-block-token-analyzer": {
"url": "https://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Code Block Token Analyzer
Open Agent mode in chat and ask: "Using Code Block Token Analyzer, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"code-block-token-analyzer": {
"url": "https://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Code Block Token Analyzer
Ask Copilot: "Using Code Block Token Analyzer, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"code-block-token-analyzer": {
"url": "https://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Code Block Token Analyzer
Open Cascade and ask: "Using Code Block Token Analyzer, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"code-block-token-analyzer": {
"url": "https://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Code Block Token Analyzer
Ask Cline: "Using Code Block Token Analyzer, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add code-block-token-analyzer --transport http "https://edge.vinkius.com/vk_preview_61f6ADAlqbkiYiLN3Wz2ZyPTCqypN7kItzL4JuPb/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Code Block Token Analyzer
Ask Claude: "Using Code Block Token Analyzer, show me...". 3 tools are ready
Where the request belongs
Work Code Block Token Analyzer can move forward.
This is for developers and technical writers who are constantly hitting context limits or trying to optimize prompts for large codebases.
Software Engineer
Checking if a massive source file will fit into a single prompt without losing context.
Technical Writer
Ensuring documentation files have correctly formatted code blocks before processing them with an agent.
Prompt Engineer
Calculating the exact token cost of code-heavy instructions to keep costs down and performance high.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse Connectors
Special Character Token Analyzer
Analyze the impact of special characters on tokenization density.
Truncation Detection Calculator
A deterministic engine for identifying and managing text truncation based on token limits.
Test Assertion Density Calculator
Detects empty or ineffective test scaffolding by calculating the ratio of assertions to test blocks.
Multi-Modal Token Calculator
Deterministic token estimation for text, image, and audio across major LLM architectures.
Number Compression Calculator
Analyze text to calculate potential token savings by rounding large numbers.
Multi-Language Token Estimator
Analyze text composition and estimate token counts across multiple languages.
Bring your own AI
Change the model, client or framework. Keep Code Block Token Analyzer connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Code Block Token Analyzer.
The practical details behind the request, access and result.
How does the Code Block Token Analyzer calculate tokens?
It uses specific heuristics where code tokens are estimated at 3 characters each and non-code text is estimated at 4 characters each. This provides a more accurate representation of how code consumes context compared to standard text.
Can I use Code Block Token Analyzer to fix broken code blocks?
It won't rewrite your code, but it will tell you if your triple-backtick blocks are missing or malformed so you can fix them before your agent tries to read them.
Will the Code Block Token Analyzer help me save money on API costs?
Yes. By identifying code-heavy files and providing exact token counts, you can more effectively prune unnecessary text and stay within efficient usage limits.
Is the Code Block Token Analyzer compatible with Cursor?
Yes, this MCP works with any MCP-compatible client, including Cursor, Claude, and Windsurf.
Does the Code Block Token Analyzer work for plain text files?
It works for any text, but its primary value is in analyzing files that contain code blocks. For plain text, it will simply provide the standard text token estimates.
One connection away
Give your agent a direct line to Code Block Token Analyzer.
Connect Code Block Token Analyzer once. Keep it beside 6,400+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available