RuleDrift MCP server

by ri7in·io.github.ri7in/rule-drift·v0.1.1

No reviews yet

Test whether AI agents retain critical instructions as conversations grow.

A92/100grade A

Write a review Install

What users say

No reviews yet

Be the first

Safety scan

A92/100

full report

Adoption

Growing

0 stars71 downloads/wk

Reviews

Write one

Nobody has reviewed RuleDrift yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

RuleDrift tools (2, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

run_suitewrite action
Run every configured conversation and isolated rule probe. Response bodies are omitted from the returned report.
validate_suite
Validate a RuleDrift configuration without calling its model or command adapter.

Public scan report

scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it

no findings

Code scan41 source files scanned25/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 0 days ago15/15
Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

How RuleDrift compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score: 92/100; higher than 95% of 48,255 servers
Tools: 2; the typical server has 7
Tools that change things: 50%; typical: 0%. Fewer write tools means less an agent can break
Downloads a week: 71; more than 54% of 12,191 servers with a package

What its tools let an agent do: 1 read · 1 run or deploy

Install RuleDrift in Claude Code, Cursor or VS Code

Runs npx -y rule-drift on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add rule-drift -- npx -y rule-drift

Add to Cursor

What the publisher says

From the RuleDrift repository's README, as published. We do not edit it. Read it on GitHub

RuleDrift Catch the moment your agent drifts from its rules.

RuleDrift tests whether an AI agent still follows important instructions after a conversation becomes long or distracting.

Run it like a test suite when you change a prompt, model, memory system, or agent workflow. It runs locally and does not sit in front of production requests.

Quick start

Requires Node.js 22+ and Ollama.

ollama pull qwen3:1.7b
npx rule-drift init
npx rule-drift test

No paid model API, account, backend, or telemetry is required.

What you get

The first conversation point where a rule fails
Terminal, JSON, and JUnit reports
Local Ollama and bring-your-own-agent support
Optional MCP tools for AI coding clients
Stable exit codes for CI

MCP

npx -y rule-drift mcp --root /path/to/your/project

See the MCP setup guide for client configuration and safety details.

Documentation

Full guide
All documentation

Contributions are welcome—see CONTRIBUTING.md. Licensed under MIT.

Nothing above is checked by us. What we check is on the safety report.

RuleDrift: common questions

Is RuleDrift MCP server safe?: Yes, by our scan: it is graded A (92/100). Read the RuleDrift safety report
How do I install RuleDrift?: It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does RuleDrift need an API key?: Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is RuleDrift maintained?: The last commit was in the last day (2026-11-03). The latest release is v0.1.1.
How does RuleDrift compare with other MCP servers?: safety score 92/100 (higher than 95% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.