MCP MeasureMCP Measure

index observed

Token Counter

Counts tokens under OpenAI-compatible (tiktoken) encodings, by model or encoding name.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
93%
Naming quality
80%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~175Tokens (tool definitions)
~1.3 KBTypical response size
Minimal attention impact (0.14% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "token-counter": {
      "url": "https://apished.com/mcp/v1/tokens"
    }
  }
}

Remote endpoints

https://apished.com/mcp/v1/tokensstreamable-http

What it can do

Tool inventory

Tools (1)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢tokens_count(text, model, encoding)

Counts tokens under an OpenAI-compatible (tiktoken) encoding. Provide exactly one of model (e.g. "gpt-4o") or encoding ("o200k_base" or "cl100k_base"). No Claude/Anthropic tokenizer.

Input Schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    },
    "model": {
      "type": "string",
      "description": "e.g. gpt-4o; exactly one of model/encoding"
    },
    "encoding": {
      "type": "string",
      "description": "o200k_base or cl100k_base; exactly one of model/encoding"
    }
  },
  "required": [
    "text"
  ],
  "additionalProperties": false
}

Output Schema

{
  "type": "object",
  "properties": {
    "tokens": {
      "type": "integer"
    },
    "encoding": {
      "type": "string"
    }
  },
  "required": [
    "tokens"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded1 tools
verifiedversion not recorded1 tools