# contextcut-mcp

> contextcut-mcp — j-straber-contextcut-mcp. Use this tool when you need to optimize code context for large language models (LLMs) and AI coding agents, reducing unnecessary information and improving performance. The contextcut-mcp tool prunes abstract syntax tree (AST) code context locally, providing a more efficient input for agents like Claude, Cursor, and Antigravity via the MCP interface. It integrates with git, allowing for seamless optimization of code repositories.

Canonical page: https://skillsregistry.net/skills/j-straber-contextcut-mcp  
JSON: https://api.skillsregistry.net/v1/skills/j-straber-contextcut-mcp

## Description

Local-first AST code context pruner for LLMs & AI coding agents (Claude, Cursor, Antigravity) via MCP.

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/j-straber/contextcut-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": "j-straber-contextcut-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/j-straber-contextcut-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/j-straber-contextcut-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