MGI-Mind runs on your own machine — the client starts it, so there is no endpoint to ping. 31 installs a week from npm. Last commit 21 Oct 2026.
Local memory server for AI agents: hybrid search, a fact graph and a hash-chained audit log.
We read the source, 4 d ago · rules 995398eba69f
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.
postinstall: node lib/install.js
const child = spawn(bin, process.argv.slice(2), { stdio: "inherit" });
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
.nodeColor(nodeColor).nodeVal(nodeSize).nodeLabel(()=>'').linkColor(linkColor)
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 mgi-mind -- npx -y mgi-mind
{
"mcpServers": {
"mgi-mind": {
"command": "npx",
"args": [
"-y",
"mgi-mind"
]
}
}
}
[mcp_servers.mgi-mind]
command = "npx"
args = ["-y", "mgi-mind"]
{
"mcpServers": {
"mgi-mind": {
"command": "npx",
"args": [
"-y",
"mgi-mind"
]
}
}
}
{
"servers": {
"mgi-mind": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mgi-mind"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MGIMIND_HOME (Where the memory store lives. Defaults to ~/mgimind).
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
Stock research memory for Claude: theses, sourced claims and SEC filing alerts in a local graph
Open-source MCP server: encrypted local keys and state, operator approval gates, a hash-chained log.
Local-first secret scanning, rotation, vault, and audit-log tools for AI agents.
Verifiable action logs for AI agents. Every action is recorded in a SHA-256 hash chain.
Docker for AI agents — containers, compose stacks, logs and databases, locally or over SSH.
Persistent memory for AI agents — log and recall conversation context over MCP.
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
Answers built from our own checks of this server.