# ai-usage-mcp

> ai-usage-mcp — mohitbansal321-ai-usage-mcp. Use this tool when you need to track and manage AI usage metrics, such as token counts, client and model usage, and associated costs, with a local-first approach. It solves problems related to AI resource monitoring and cost estimation, providing insights into usage patterns and expenses. The tool takes in local data as input and outputs detailed usage reports and cost estimates, making it ideal for developers and users seeking transparency and control over their AI usage.

Canonical page: https://skillsregistry.net/skills/mohitbansal321-ai-usage-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mohitbansal321-ai-usage-mcp

## Description

A local-first MCP server that answers, from real data on your machine:  How many tokens have I used, from which client, model and session — and what did it cost?

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/MohitBansal321/ai-usage-mcp)

## 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": "mohitbansal321-ai-usage-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mohitbansal321-ai-usage-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mohitbansal321-ai-usage-mcp/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