AI code review agent MCP server. Reviews code like a kernel maintainer: blunt, technical, no sugarcoating. Detects bugs + OWASP Top 10 security vulnerabilities. 4 harshness levels. Anti-RLHF.
AI code review agent that doesn't sugarcoat. If your code is bad, it tells you. Bluntly.
An AI-powered MCP (Model Context Protocol) server that reviews your code the way experienced maintainers review patches on serious projects: technically, directly, without diplomacy.
- AI code review — reviews code snippets, files, git diffs, and commits - Returns findings with severity labels: CRITICAL, MAJOR, MINOR, NIT, CLEAN - Cites specific line numbers for every finding - Explains why something is bad, then how to fix it - Ends with a clear verdict: "Ship it." or "Do not merge until..." - No false praise. No hedging. No apologies. No filler.
Most AI code reviewers are trained to be polite. They preface criticism with "great work but...", they hedge with "you might want to consider...", they soften findings with "this could potentially be an issue".
That's not how serious code review works. On real projects (Linux kernel, PostgreSQL, Redis, SQLite), maintainers review patches directly. They find problems and call them out clearly. They don't exist to make the author feel good — they exist to make the code better.
This MCP encodes that tradition. The personality IS the product.
LLMs are RLHF-trained to be polite. This AI agent fights that with three layers:
1. System prompt — 12 core principles (code-not-coder, verdict-first, severity labels, line citations, no false praise, no hedging, no apologies, no filler, second person, no demographic references, no refusal, no hallucinated bugs) 2. Post-processor — strips 40+ banned phrases (hedging, softeners, apologies, filler) from
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/frangelbarrera--code-review-agent-mcp.html)
🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
00200200/usagetrimKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
Alpha-Park/genpark-ast-import-dependency-rewriter-skillToken-safe AST import re-aliasing and dependency migration engine safely replacing module paths and callsites without regex bugs.
alphaparkinc/genpark-ast-import-dependency-rewriter-skillToken-safe AST import re-aliasing and dependency migration engine safely replacing module paths and callsites without regex bugs.
Alpha-Park/genpark-codebase-dead-code-unreachable-pruner-skillAST-level static call-graph analyzer and dead code pruner identifying orphaned functions, unreachable methods, and token-bloat clusters.
alphaparkinc/genpark-semver-breaking-change-auditor-skillSemantic versioning (SemVer 2.0) breaking change auditor inspecting AST public API surface diffs, parameter reordering, and removed exports.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.