memi runs on your own machine — the client starts it, so there is no endpoint to ping. 1 612 installs a week from npm. Last commit 9 Sep 2026.
Memi is the read-only design engineering audit and skill layer for coding agents.
We read the source, 21 h ago · rules 3dff92dd89df
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 child = spawn(executable, args, {
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(executable, args, {
const target = path.join(input.captureRoot, capture.artifactName);
console.log(`\n${ui.fail(`Update failed. Try manually: ${formatUpdateFailureGuidance(latest)}`)}\n`);
el.innerHTML = html;
"Preserve npm’s effective cache, including .npmrc configuration, before packed and upgrade installers isolate their environment. Only the cache path is forwarded; credentials remain excluded. Prefer verified cached packages with network fallback and label install timeouts…
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 memi 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 memi -- npx -y @memi-design/cli
{
"mcpServers": {
"memi": {
"args": [
"-y",
"@memi-design/cli"
],
"command": "npx"
}
}
}
[mcp_servers.memi]
command = "npx"
args = ["-y", "@memi-design/cli"]
{
"mcpServers": {
"memi": {
"args": [
"-y",
"@memi-design/cli"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"memi": {
"args": [
"-y",
"@memi-design/cli"
],
"command": "npx"
}
}
}
Memi is the design layer for agentic AI.
Memory, docs, and repo context layer for engineering agents.
Read-only GCP tools for debugging incidents and finding cost savings
Self-hosted multi-agent collaboration and audit layer for AI-assisted engineering teams
Memory for coding agents: the decisions, the dead ends, and where the last session stopped.
Local design engine for AI agents: create, edit and export real, editable designs.
Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.
MCP server for Microsoft Entra ID sign-in and audit-log triage (read-only)
Answers built from our own checks of this server.