# Token Counter

> Token Counter — com-apished-token-counter. Use this tool when you need to accurately count tokens in text data, solving problems like optimizing input lengths for AI models or tracking token usage. It takes text input and model or encoding name, and outputs the corresponding token count under OpenAI-compatible encodings. Ideal for use cases where precise token counting is crucial, such as fine-tuning AI models or managing token-based quotas.

Canonical page: https://skillsregistry.net/skills/com-apished-token-counter  
JSON: https://api.skillsregistry.net/v1/skills/com-apished-token-counter

## Description

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

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.apished%2Ftoken-counter)

## Use it

MCP endpoint published by the skill: `https://apished.com/mcp/v1/tokens`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "com-apished-token-counter"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-apished-token-counter` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-apished-token-counter/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt