# ContextGC

> Use this tool when you need to optimize MCP server performance by compressing code context. ContextGC solves the problem of excessive token usage by extracting code skeletons and expanding functions on demand, reducing token usage by 70-90%. It takes in code inputs and outputs compressed context, making it ideal for use cases where efficient context loading is crucial.

Canonical page: https://skillsregistry.net/skills/superzavier-contextgc-mcp  
JSON: https://api.skillsregistry.net/v1/skills/superzavier-contextgc-mcp

## Description

基于AST解析的上下文智能压缩MCP服务器，通过提取代码骨架和按需展开函数，节省70-90% token，并支持渐进式上下文加载。

## Trust

- **Trust score (0–1):** 0.99
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ygx7otxqum)
- **Repository:** <https://github.com/superZavier/contextgc-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": "superzavier-contextgc-mcp"
    }
  }
}
```

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