# token-optimization-mcp

> Use this tool when you need to optimize large language model (LLM) usage costs and efficiency, especially in offline environments. It solves problems related to token estimation, prompt compression, and model routing, providing inputs such as prompts and models, and outputs optimized token usage and routing plans. Ideal for use cases where reducing LLM costs and improving performance is crucial, such as in resource-constrained or high-traffic applications.

Canonical page: https://skillsregistry.net/skills/dcx7c5-token-optimization-mcp  
JSON: https://api.skillsregistry.net/v1/skills/dcx7c5-token-optimization-mcp

## Description

A fully offline MCP server for token estimation, prompt compression, model routing, and semantic caching to optimize LLM usage costs and efficiency.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **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/k3bz43i62x)
- **Repository:** <https://github.com/DCx7C5/token-optimization-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": "dcx7c5-token-optimization-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/dcx7c5-token-optimization-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/dcx7c5-token-optimization-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