# Claudexor

Claudexor routes coding agents through one typed interface. Use it to compare proposed changes and inspect results before applying them.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 518
- Author: razzant
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/razzant/claudexor
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/claudexor

## What it does

Claudexor runs connected coding tools through a shared typed interface. Read-only questions can resume a tool’s native session, while write turns return patches or complete file manifests. You can compare multiple runs and send their results for independent review and arbitration.

The server runs locally, treats files as the source of truth, and collects no telemetry. It also supports budget and quota accounting, protected paths, and deterministic gates. You need Node.js `24.15` or later and either a logged-in vendor CLI or an API key; Git is needed for Git-backed workflows. Check the runtime requirement before launching it through `npx`.

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

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add claudexor -- npx -y claudexor
```

### Codex

**Platform CLI**
```bash
codex mcp add claudexor -- npx -y claudexor
```

### Cursor

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

### GitHub Copilot

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

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add claudexor npx -y claudexor
```

## When to use it
- compare outputs from multiple agent runs
- resume a native session for a read-only question
- review changes as patches or file manifests
- track connected agents’ budgets and quotas
- protect paths and gate changes

## Example prompts
- Compare approaches to this task by running agents through Claudexor, then show me the differences.
- Answer this project question by resuming the native session through Claudexor without changing files.
- Return the proposed changes as a reviewable patch and check them with an independent run.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43872

---
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