MELRA runs on your own machine — the client starts it, so there is no endpoint to ping. 722 installs a week from npm. Last commit 25 Oct 2026.
Local MCP runtime for policy-governed, verified agent actions with durable receipts.
We read the source, 32 min ago · rules 995398eba69f
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.
"doas", "gsudo", "ksu", "pfexec", "pkexec", "run0", "runas", "runuser", "su",
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.
existsSync("/.dockerenv") || existsSync("/run/.containerenv"),
const child = spawn(claude, claudeLaunchArgv(file, passed), { cwd: env.workspaceRoot, stdio: "inherit" });
COPY package.json pnpm-lock.yaml pnpm-workspace.yaml tsconfig.base.json .npmrc ./
...Object.fromEntries(Object.entries(process.env).filter(([name]) => !withheld.has(name.toUpperCase()))),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch MELRA and you get told the day something new turns up.
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 melra -- npx -y @melra/cli
{
"mcpServers": {
"melra": {
"command": "npx",
"args": [
"-y",
"@melra/cli"
]
}
}
}
[mcp_servers.melra]
command = "npx"
args = ["-y", "@melra/cli"]
{
"mcpServers": {
"melra": {
"command": "npx",
"args": [
"-y",
"@melra/cli"
]
}
}
}
{
"servers": {
"melra": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@melra/cli"
]
}
}
}
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Pre-execution policy gate for consequential agent actions with durable trust receipts.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Portable signed records for agent, API, MCP, and cross-runtime interactions.
Ed25519-signed receipts for every AI agent action. Local-first, verifiable, no server required.
Prevent duplicate AI-agent side effects with idempotency, verification, and durable receipts.
Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
Per-principal census of MCP subscriptions and durable tasks, with verified-stop receipts.
Answers built from our own checks of this server.