Vnsh runs on your own machine — the client starts it, so there is no endpoint to ping. 126 installs a week from npm. Last commit 6 Sep 2026.
Portable workspaces for AI agents: one encrypted link any agent can read and write
What the code does
We read the source, 2 h ago · rules 3dff92dd89df
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.
const child = spawn(command[0] as string, command[1] as string[], {
const file = path.join(current, name);
const OG_SITE_PNG = 'iVBORw0KGgoAAAANSUhEUgAABLAAAAJ2CAMAAAB4notuAAAAwFBMVEX////+/v78/Pz5+fn29vby8vLt7e3p6enk5OTe3t7U1NTHx8e7u7sixV4hwFy0tLSpqamjo6OhoaGgoKCcnJyXl5eRkZGJiYmDg4N9fX0+jFtzc3MXczlvb29ra2tnZ2diYmJdXV1XV1dTU1NSUlIVYjFQUFBMTExJSUlDQ0M2Pjk4ODgzMzMwMDAoLiopKSkmJiYjIyMaIx0…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 vnsh -- npx -y vnsh-mcp{
"mcpServers": {
"vnsh": {
"args": [
"-y",
"vnsh-mcp"
],
"command": "npx"
}
}
}[mcp_servers.vnsh]
command = "npx"
args = ["-y", "vnsh-mcp"]{
"mcpServers": {
"vnsh": {
"args": [
"-y",
"vnsh-mcp"
],
"command": "npx"
}
}
}{
"mcpServers": {
"vnsh": {
"args": [
"-y",
"vnsh-mcp"
],
"command": "npx"
}
}
}Alternatives to Vnsh
same job, measured the same wayPersistent docs and memory for AI agents — read, write, organize & search a shared workspace.
Markdown workspace for AI agents: read, write, organize, and share markdown documents.
Store, retrieve, and pin encrypted files on IPFS via MCP tools for AI agents and workflows
Local SQL workspaces with bounded, recoverable writes for coding agents.
Local design engine for AI agents: create, edit and export real, editable designs.
Owned, portable working memory: a plain-files markdown brain any model can read and cite.
Disposable inboxes for AI agents and CI: catch the verification email, read the OTP or link.
Persistent cross-model memory for AI agents: verifiable, portable, client-side encrypted.
Vnsh — questions
Answers built from our own checks of this server.