# Skim MCP Server

> Use this tool when you need to optimize large codebases for language model processing, as it compresses code by 60-95% to improve context optimization for LLMs, taking in original code as input and outputting compressed code. It solves the problem of inefficient code processing, enabling faster and more accurate language model performance. Ideal for use cases where code size and complexity hinder LLM efficiency.

Canonical page: https://skillsregistry.net/skills/io-github-luw2007-skim-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/io-github-luw2007-skim-mcp-server

## Description

MCP server for Skim code transformation. Compresses code 60-95% for LLM context optimization.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.3
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-09

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.luw2007%2Fskim-mcp-server)

## 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": "io-github-luw2007-skim-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-luw2007-skim-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-luw2007-skim-mcp-server/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