Explore
Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
Every listed MCP server and skill. Filter by where it runs, what it needs, and how it is licensed.
1–12 of 83 tools for “review”
Clear allThe Architecture Review Agent is an open-source AI agent sample that reviews software architectures and generates interactive diagrams automatically.
official/skill/MIT/★ 106/no key
Automated PRISMA 2020 systematic literature review with AI-assisted screening via MCP. Works with Claude, Codex, Copilot, Cursor, and any MCP-compatible agent.
skill/MIT/★ 11/no key
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo w
python/MIT/★ 32k/no key
Local-first MCP plugin for continuous software-quality review by AI coding agents, powered by Jev.
skill/MIT/★ 242/no key
Review-only AI code review for GitHub pull requests. Cross-check PRs with model-agnostic reviewers that can comment inline but cannot approve, merge, or close.
skill/MIT/★ 19/no key
agy-plugin-cc is a Claude Code companion for running Gemini CLI or Antigravity CLI (agy) as a cross-model task delegate and code reviewer, with pragmatic and adversarial review, MCP tools, and backgro
skill/MIT/★ 14/no key
An agentic law firm. Yours. 67 specialist AI agents that review documents through evidence-backed debate, with mandatory human gates and a 10-pass verification loop. Apache 2.0.
skill/Apache-2.0/★ 311/no key
Cheaper and better Greptile alternative runs on your own github actions.
node.js/MIT/★ 122/no key
Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.
python/Apache-2.0/★ 76/no key
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate, and score: the model judges, policy decides auto, review, o
python/MIT/★ 72/no key
Opinionated Go skill for Claude Code, Codex, Cursor, Copilot & OpenCode — architecture, modern Go, testing, code review, MCP & agent patterns.
skill/MIT/★ 30/no key
Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code uploa
node.js/MIT/★ 82/no key
Who stands behind it
Who stands behind it