Developer · Local MCP server
cmdxray
Offline MCP server: explains shell commands token-by-token and flags destructive ones for AI agents.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.aurelio-nakamura/cmdxray- Version
- 0.26.1
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- npm
- Published
- 2026-09-19
- Updated
- 2026-09-19
- Publisher
- aurelio-nakamura (GitHub) · 2 servers with pages here
- Website
- aurelio-nakamura.github.io/cmdxray/
- Repository
- github.com/aurelio-nakamura/cmdxray
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | cmdxray | 0.26.1 | stdio |
How to connect cmdxray
cmdxray runs locally from a Node.js package published to the npm registry: cmdxray version 0.26.1. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y cmdxray@0.26.1.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"cmdxray": {
"command": "npx",
"args": [
"-y",
"cmdxray@0.26.1"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More from aurelio-nakamura (GitHub)
| Server | Runs |
|---|---|
| DataloupeOffline MCP server to explore CSV/JSON/Parquet/Excel: preview, query, diff, render interactive HTML. | Local · stdio |
More developer servers
| Server | Runs |
|---|---|
| CloudwrightCloud architecture and migration planning with costs, controls, evidence, and deployable IaC. | Local · stdio |
| Clover PublicJob search and interview prep MCP. 15 tools, OAuth 2.1, cross-LLM. four-leaf.ai. | Remote · HTTP |
| CLS++ MemoryCross-LLM persistent memory: store context once, recall it from any AI model. | Remote & Local · HTTP, stdio |
| CludePortable agent memory anchored on Solana. Local SQLite + vector recall, open export. | Local · stdio |
| CNAPS.ai MCP ServerRun 70+ AI models and 50+ tools on CNAPS Studio in natural language — Claude, n8n, or Zapier. | Remote · HTTP |
| Co Eli MCPMCP server for Colombian Constitutional Court case law (datos.gov.co), citation verification. | Local · stdio |
| Coach IcarusAdaptive running coach MCP server — training data, plans, and recovery for AI assistants. | Remote · HTTP |
| Coach MCPAdaptive AI training coach MCP server backed by Garmin Connect. | Local · stdio |