Tiktoken MCP

An MCP (Model Context Protocol) server that provides token counting functionality using OpenAI's tiktoken library.

- 🔢Token Counting: Count tokens for any text using various tiktoken encodings
- 💰Cost Estimation: Estimate token costs for popular AI models (GPT-4, Claude, etc.)
- 🚀Easy to Use: Run directly withnpx- no installation required
- 🔧Claude Desktop Integration: Seamlessly integrates with Claude Desktop app

You can run this MCP server directly using npx:

- Node.js 16 or higher
- Python 3.6 or higher
- pip (Python package manager)

The tiktoken Python library will be automatically installed when you first run the package.

Count tokens in text using various tiktoken encodings.

- text(required): The text to count tokens for
- model(optional): The encoding model to use. Options: 'cl100k_base' (default), 'p50k_base', 'p50k_edit', 'r50k_base'

Estimate token costs for various AI models.

- text(required): The text to estimate cost for
- model(required): The model to estimate cost for. Options: 'gpt-4', 'gpt-4-turbo', 'gpt-3.5-turbo', 'claude-3-opus', 'claude-3-sonnet', 'claude-3-haiku'

To use this MCP server with Claude Desktop, add the following to your Claude configuration file:

Location:~/Library/Application Support/Claude/claude_desktop_config.json

Location:%APPDATA%\Claude\claude_desktop_config.json

{ "mcpServers": { "tiktoken": { "command": "npx", "args": ["tiktoken-mcp"] } } }

After adding this configuration, restart Claude Desktop. You should then be able to use the token counting tools in your conversations.

Once configured, you can use the tools like this:

- "Count the tokens in this text: 'Hello, world!'"
- "Estimate the cost of this prompt for GPT-4"
- "How many tokens are in this paragraph using the cl100k_base encoding?"

Token count: 13 Model: cl100k_base First 100 token IDs: 9906, 11, 1917, 0, 498, 1097, 701, 30, 220, 17, ...

Token count: 150 Model: gpt-4 Estimated input cost: $0.004500 Estimated output cost: $0.009000 Total cost (if used as both input and output): $0.013500

This MCP server uses Python's tiktoken library under the hood to accurately count tokens. It supports multiple encoding models:

- cl100k_base: Used by GPT-4, GPT-3.5-turbo, and newer models
- p50k_base: Used by Codex models
- p50k_edit: Used by edit models
- r50k_base: Used by GPT-3 models

Contributions are welcome! Please feel free to submit a Pull Request.

If you encounter any problems, please file an issue on theGitHub repository.

Anchor Browser (https://anchorbrowser.io) is secure infrastructure for computer-use agents — stealth cloud browsers, authentication, captcha bypass, and a hosted MCP server for Cursor, Claude, and Windsurf.