Robrain runs on your own machine — the client starts it, so there is no endpoint to ping. 633 installs a week from npm. Last commit 3 Nov 2026.
Self-hosted decision memory for AI coding agents; warns before re-proposing a rejected approach.
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.
execSync(cmd, { input: output })
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.
…e[o]}}),Qe("at");var Ze=function(t,e){return b(i[t].prototype[e])},tr=(Ze("Array","at"),TypeError),er=function(t,e){if(!delete t[e])throw new tr("Cannot delete property "+Y(e)+" of "+Y(t))},rr=Math.min,nr=[].copyWithin||function(t,e){var r=it(this),n=de(r),o=he(t,n),i=he(e,n),a=a…
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 robrain -- npx -y robrain
{
"mcpServers": {
"robrain": {
"command": "npx",
"args": [
"-y",
"robrain"
]
}
}
}
[mcp_servers.robrain]
command = "npx"
args = ["-y", "robrain"]
{
"mcpServers": {
"robrain": {
"command": "npx",
"args": [
"-y",
"robrain"
]
}
}
}
{
"servers": {
"robrain": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"robrain"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
PERCEPTION_API_URL (Perception API URL. Optional — read from ~/.robrain/config.json after `npx robrain up`), PERCEPTION_API_KEY (Perception API key. Optional — read from ~/.robrain/config.json after `npx robrain up`).
Persistent decision memory for AI agents: rationale, rejected approaches, and entity history.
Coding agent memory — one local MCP server for every project. Warns before repeating failed fixes.
Local decision memory for coding agents: record decisions with limits, search precedents, supersede.
Shared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
Shared project memory for coding agents: decisions, lessons, guardrails and tasks per repository.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
Answers built from our own checks of this server.