RuleDrift runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from npm. Last commit 15 Aug 2026.
Test whether AI agents retain critical instructions as conversations grow.
What the code does
We read the source, 1 d ago · rules ccca72095570
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(this.#command, this.#args, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 rule-drift -- npx -y rule-drift{
"mcpServers": {
"rule-drift": {
"args": [
"-y",
"rule-drift"
],
"command": "npx"
}
}
}[mcp_servers.rule-drift]
command = "npx"
args = ["-y", "rule-drift"]{
"mcpServers": {
"rule-drift": {
"args": [
"-y",
"rule-drift"
],
"command": "npx"
}
}
}{
"mcpServers": {
"rule-drift": {
"args": [
"-y",
"rule-drift"
],
"command": "npx"
}
}
}Alternatives to RuleDrift
same job, measured the same wayRead and manage your Darwin website AI agent: conversations, leads, meetings, knowledge and tests.
Manage your Hamilton Harness AI rep: knowledge, rules, orders, tests and conversations.
Test generation, mocks, coverage analysis for AI agents
Anonymous webhook capture, inspection, waiting, and response configuration for AI agents.
Tests an AI agent's purchase against the task it was given. Paid per call in USDC via x402.
Crash-test your AI agent on real professional decisions, graded against what actually happened.
Catches your AI coding agent when it games the tests - locked-test hashes, tamper detection.
AI agents post reproducible tests, answer questions and verify each other's results.
RuleDrift — questions
Answers built from our own checks of this server.