Once runs on your own machine — the client starts it, so there is no endpoint to ping. 460 installs a week from npm. Last commit 22 Sep 2026.
Execution-safety MCP for AI coding agents protecting consequential writes from unsafe retries.
We read the source, 7 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(
path.join(
onceDirectory,
"backups",
candidate.callsite_ref
);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 once -- npx -y @once-agent/mcp
{
"mcpServers": {
"once": {
"args": [
"-y",
"@once-agent/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.once]
command = "npx"
args = ["-y", "@once-agent/mcp"]
{
"mcpServers": {
"once": {
"args": [
"-y",
"@once-agent/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"once": {
"args": [
"-y",
"@once-agent/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
ONCE_API_KEY (Optional Once Cloud API key. Required only for tools or integrations that contact Once Cloud, such as once_verify_connection.).
The author declared them in the registry entry; get the values from the project itself.
Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.
Authorize consequential AI agent actions before execution
Local test execution and coverage summaries for onboarding agents.
Project management MCP for AI agents with safe task reads and writes.
Local coding tools for ChatGPT Developer Mode and MCP clients with safe editing and shell execution.
Structured execution for coding agents: contracts, postconditions, gates, guardrails.
Real-time semantic security for AI coding agents and MCP tools
Merge gates and safety checks for AI coding agents via MCP.
Answers built from our own checks of this server.