MCPLow riskUnclaimed

RuleDrift

Test whether AI agents retain critical instructions as conversations grow.

ri7inri7in/rule-drift★ 1Updated Aug 14, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.ri7in/rule-drift",
  "description": "Test whether AI agents retain critical instructions as conversations grow.",
  "title": "RuleDrift",
  "repository": {
    "url": "https://github.com/ri7in/rule-drift",
    "source": "github"
  },
  "version": "0.1.1",
  "packages": [
    {
      "registryType": "npm",
      "identifier": "rule-drift",
      "version": "0.1.1",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "value": "mcp",
          "type": "positional"
        }
      ]
    }
  ]
}

Permissions

DeclaredDetected
Runs code—node
Installs—npm:rule-drift@0.1.1
Runs install scripts—None
NetworkNoneNone
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #10.1.1latestOct 7, 2026