Code review mcp servers

30,539 tagged Code review, measured the same way as everything else here.

Browse within: code-quality 13code-intelligence 9code-analysis 8ai-code-review 6

bana

97

block/buzz

Agent ✓ vendor

Architecture reviewer — big picture, simplicity, integration.

32k +340 today A 13 tokens original Apache-2.0

rust-code-quality

98

rustfs/rustfs

Skill Claude CodeCodex

Run a focused Rust quality review when the user requests one, when reviewing a Rust PR/commit, or when another selected review workflow delegates Rust-specific checks. Do not auto-load for every implementation edit.

32k 3d ago A 44 tokens original Apache-2.0

pr-review

99

rustfs/rustfs

Skill Claude CodeCodex

Review a GitHub PR end-to-end from a URL or number — fetch metadata, inspect the diff, run multi-role adversarial review, check CI status, and post the review comment. Use when the user provides a PR link and asks to review it.

32k 3d ago A 55 tokens original Apache-2.0

code-review-graph

101

tirth8205/code-review-graph

MCP server Claude CodeCodexCursor +2

Local-first knowledge graph for token-efficient code review through MCP and CLI. Runs locally from the code-review-graph Python package.

31k +55 6d ago A tokens not measured original MIT

tirth8205/code-review-graph

Instructions file

Instructions for tirth8205/code-review-graph, covering claude.md - project context for claude code, project overview, graph tool usage (token-efficient), architecture and key commands.

31k +55 6d ago A 2,664 tokens original MIT

build-graph

103

tirth8205/code-review-graph

Skill Claude CodeCodex

Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

31k +55 6d ago A 27 tokens original MIT

review-delta

104

tirth8205/code-review-graph

Skill Claude CodeCodex

Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.

31k +55 6d ago A 24 tokens original MIT

review-pr

105

tirth8205/code-review-graph

Skill Claude CodeCodex

Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.

31k +55 6d ago A 27 tokens original MIT

component-reviewer

106

davila7/claude-code-templates

Agent Claude Code

Expert component reviewer for Claude Code Templates. Use PROACTIVELY when adding or modifying components in cli-tool/components/ directory (agents, commands, MCPs, hooks, settings, skills, loops). Validates format, required fields, naming conventions, and security.

30k +27 yesterday A 57 tokens original MIT

agentscope-ai/agentscope

Instructions file GitHub Copilot

Copilot instructions for agentscope-ai/agentscope, covering agentscope code review guide, 1. code quality, 2. [must] code security, 3. [must] testing & dependencies and 4. code standards.

30k +218 yesterday A 741 tokens original Apache-2.0

docs-reviewer

108

ComposioHQ/composio

Agent

Reviews documentation PRs for Composio, an SDK that connects AI agents to external tools and APIs.

30k +49 today A 0 tokens original MIT

bprr

109

wilsonfreitas/awesome-quant

Skill Claude CodeCodex

Bulk PR reviewer for awesome-quant. Use when the user asks to review all open PRs, review unreviewed PRs, bulk review, or mentions "bprr". Reviews open PRs lacking the reviewed label and presents a summary before any merge/comment/label action.

29k +44 changed today A 61 tokens

sprr

110

wilsonfreitas/awesome-quant

Skill Claude CodeCodex

Single PR reviewer for awesome-quant. Use when the user asks to review, validate, comment on, label, close, or merge one specific pull request that adds README.md entries. Triggers include "sprr", "review PR", "check PR", and "validate contribution".

29k +44 changed today A 60 tokens

comment-analyzer

111

nrwl/nx

Agent Claude Code

Use this agent during PR review to check that a PR's comments and doc-comments are TRUE. It verifies every load-bearing claim in a changed comment against the code it describes, and flags comments the diff left stale. It does not ask for more comments - this repo's committed CLAUDE.md rules default to no comment, so…

29k +11 yesterday A 122 tokens original MIT

docs-reviewer

112

nrwl/nx

Agent Claude Code

Use this agent during PR review to answer two docs questions about any PR. Coverage, on every diff - does the change alter user-facing behavior that astro-docs documents in prose, without updating those docs? Compliance, when the diff touches docs content (astro-docs/src/content/ or astro-docs/sidebar.mts) - do the…

29k +11 yesterday A 171 tokens original MIT

review-pr

113

nrwl/nx

Skill Claude CodeCodex

Deep code review of a single open PR in nrwl/nx. Checks the PR out only inside an isolated sandbox, then runs four fixed reviewers: implementation (correctness, errors, types, performance), verification (tests, ticket grounding, comments, and docs), approach, and security. A reproduce-verifier executes a runnable…

29k +11 yesterday A 118 tokens original MIT

final-release-review

114

openai/openai-agents-python

Skill Claude CodeCodex ✓ vendor

Perform pre-release planning or a final release-candidate review for openai-agents-python by comparing the target with the previous remote tag, determining the minimum compatible release type, auditing regressions and contract changes, reviewing open documentation PR coverage, drafting minor-release Key Changes, and…

29k +48 yesterday A 64 tokens original MIT

review-prs

115

can1357/oh-my-pi

Command

Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.

29k +464 today A 0 tokens original MIT

reviewer

116

can1357/oh-my-pi

Agent

Code review specialist for quality/security analysis.

29k +464 today A 10 tokens original MIT

task-checker

120

eyaltoledano/claude-task-master

Agent

Use this agent to verify that tasks marked as 'review' have been properly implemented according to their specifications. This agent performs quality assurance by checking implementations against requirements, running tests, and ensuring best practices are followed. Context: A task has been marked as 'review' after…

28k +2 4mo ago A 0 tokens

At most 3 mods per repository are shown here — the rest are on their repository pages: