# MCP TokenSage

> Use this tool when you need to monitor and optimize Large Language Model (LLM) API usage, as it provides token counting, usage tracking, and cost calculation capabilities. It solves problems related to API cost management and usage transparency, especially in applications like Cursor and Windsurf. With a proxy server mode, it automatically intercepts and monitors API requests, providing valuable insights through its tracking and calculation interface.

Canonical page: https://skillsregistry.net/skills/quangminh1212-mcp-tokensage  
JSON: https://api.skillsregistry.net/v1/skills/quangminh1212-mcp-tokensage

## Description

Enables token counting, usage tracking, and cost calculation for LLM APIs, with a proxy server mode to automatically intercept and monitor API requests from clients like Cursor and Windsurf.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ck78n9codg)
- **Repository:** <https://github.com/quangminh1212/TokenLab>

## Use it

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": "quangminh1212-mcp-tokensage"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/quangminh1212-mcp-tokensage` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/quangminh1212-mcp-tokensage/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