# ai-context-kit

Audits agent instructions across project files, spots conflicting guidelines, and monitors token overhead.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: ofershap
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ofershap/ai-context-kit
- Updated: 2026-10-21
- HTML: https://affpapa.org/en/nevibecode/mcp/ai-context-kit

## What it does

Context files pile up quickly. Instructions in `CLAUDE.md`, `.cursor/rules/`, and Copilot prompts often contradict each other. This tool audits context files and flags opposing directions or repeated lines.

The server measures the token footprint of each configuration file. It also provides a selection helper to pass only the instructions needed for a given task. Your prompt window stays lean.

Node.js must be present locally to execute the server via `npx`. You can also trigger the lint check in continuous integration, where failures stop the pipeline.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add ai-context-kit -- npx -y ai-context-kit
```

### Codex

**Platform CLI**
```bash
codex mcp add ai-context-kit -- npx -y ai-context-kit
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ai-context-kit": {
            "command": "npx",
            "args": [
                "-y",
                "ai-context-kit"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ai-context-kit": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "ai-context-kit"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add ai-context-kit npx -y ai-context-kit
```

## When to use it
- detect conflicting rules across different editor configs
- measure token usage across context files
- prune duplicate lines from prompt instructions
- spot vague guidelines in project documentation

## Example prompts
- Audit project context files for conflicting rules using ai-context-kit.
- Check how many tokens my CLAUDE.md and Cursor rules consume.
- Select context rules relevant only to the authentication task.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md