Orangerail runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 11 Aug 2026.
Turns your Prisma schema into typed MCP tools, with destructive writes gated behind human approval
We read the source, 8 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, args, { stdio: 'ignore', detached: true });
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 orangerail -- npx -y orangerail
{
"mcpServers": {
"orangerail": {
"args": [
"-y",
"orangerail"
],
"command": "npx"
}
}
}
[mcp_servers.orangerail]
command = "npx"
args = ["-y", "orangerail"]
{
"mcpServers": {
"orangerail": {
"args": [
"-y",
"orangerail"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"orangerail": {
"args": [
"-y",
"orangerail"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
DATABASE_URL (The database the generated actions reach, in the same form your Prisma datasource takes.).
The author declared them in the registry entry; get the values from the project itself.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
Capture tool workflows, save typed tools, and replay with human approval. Includes an MCP Apps UI.
Connect AI to store orders, products and inventory with scoped access and human approvals.
FHIR chart tools for MCP: read-only by default, with elicitation-gated, human-approved writes.
Gate AI agent actions behind a consent policy with human approval via Telegram. Fail-closed.
Zero-secret MCP gateway for AI agents: risk-scored, audited calls with human-in-the-loop approval.
Give your agent its own email address with graduated human oversight, from approval to autonomy.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
Answers built from our own checks of this server.