Ncp runs on your own machine — the client starts it, so there is no endpoint to ping. 166 installs a week from npm. Last commit 1 Nov 2026.
1 MCP to rule them all. Orchestrate, discover, and run any tool instantly.
We read the source, 1 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
writeFileSync(tempFile, job.parameters.code, 'utf-8');
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
const hasNcpEnvVars = Object.keys(process.env).some(key => key.startsWith('NCP_'));
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
postinstall: npm run build:if-dev
const skillDir = path.join(this.skillsDir, skillDirName);
const child = spawn(command, args, {
`Update with: ${chalk.cyan(`ncp update ${mcpInfo.name}`)}`
const hasNcpEnvVars = Object.keys(process.env).some(key => key.startsWith('NCP_'));
const files = await fs.readdir(photonDir);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ncp -- npx -y @portel/ncp
{
"mcpServers": {
"ncp": {
"command": "npx",
"args": [
"-y",
"@portel/ncp"
]
}
}
}
[mcp_servers.ncp]
command = "npx"
args = ["-y", "@portel/ncp"]
{
"mcpServers": {
"ncp": {
"command": "npx",
"args": [
"-y",
"@portel/ncp"
]
}
}
}
{
"servers": {
"ncp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@portel/ncp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NCP_DEBUG (Enable debug logging for troubleshooting), NCP_MODE (Operating mode: 'mcp' for AI assistant integration or 'cli' for command-line), NO_COLOR (Disable colored output in logs and CLI).
Route one agent through one MCP server to many, with progressive tool discovery to shrink context.
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration
Laviya AI Orchestration MCP runtime for IDE and agent integrations.
Forge orchestrator MCP server for Claude Code (alpha). Codex/Gemini runners are not in the alpha.
Discover, run, inspect, build, test, and privately reuse AI workflows.
Per-env roadmap board for WithVibe — an MCP server the orchestrator drives to plan and track work.
AI agent interface to Apache DolphinScheduler: 58 MCP tools for workflow orchestration & data ops.
Answers built from our own checks of this server.