Best MCP servers for code review
69 MCP servers in the Official MCP Registry do code review. 30 can be used as a hosted endpoint, with nothing to install, and 54 publish their source code.
| # | Tool | Relevance | Connect | Code | Seen |
|---|---|---|---|---|---|
| 51 | invigil Linters check your code. Invigil checks whether your repo is legible — to newcomers and AI agents. | In description linters | HOSTEDLOCAL | Open | 2d ago |
| 52 | kadlint Korean ad-compliance linter for cosmetics and health-food marketing copy | In description linter | HOSTEDLOCAL | Open | 2d ago |
| 53 | git-enhanced Enhanced Git MCP Server - Code review, commit analysis, and branch management | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 54 | diffpilot MCP server for PR code review, commit messages, changelogs, and secret detection. | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 55 | OmniGlyph Local symbol ground truth MCP server for Unicode lookup and code-symbol linting. | In description linting | HOSTEDLOCAL | Open | 2d ago |
| 56 | defluff Deterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés. | In description linter | HOSTEDLOCAL | Open | 2d ago |
| 57 | rrubocop Fast RuboCop-compatible Ruby linter with MCP inspect and autocorrect tools. | In description linter | HOSTEDLOCAL | Open | 2d ago |
| 58 | Reado Your code review comments from Reado, the read-first IDE, as context and tools for your agent. | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 59 | Boltwork AI services via Bitcoin Lightning — PDF summarisation, code review, translation and more. | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 60 | Hated WoW MCP MCP server for WoW addons: Lua API, Blizzard UI source, CVars, art lookup, linting, scaffolding. | In description linting | HOSTEDLOCAL | Open | 2d ago |
| 61 | Grok Build Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research. | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 62 | physbound Physical Layer Linter: validates RF and radar calculations against hard physical limits. | In description linter | HOSTEDLOCAL | Open | 2d ago |
| 63 | Java All Call Graph Server MCP server for Java call graph generation, static analysis, method chains & config management | In description static analysis | HOSTEDLOCAL | Open | 2d ago |
| 64 | ui-ticket-mcp Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP. | In description code review | HOSTEDLOCAL | Open | 2d ago |
| 65 | dxpert.ai — free UNS tools (no API key) Free Sparkplug B topic linting, UNS naming checks and AI-readiness screening. No API key. | In description linting | HOSTEDLOCAL | Open | 2d ago |
| 66 | ruchy-mcp MCP server for Ruchy: code analysis, scoring, linting, formatting, and transpilation tools | In description linting | HOSTEDLOCAL | — | 2d ago |
| 67 | Frappe Inspector Static analysis tools for Frappe Framework and ERPNext projects via local stdio MCP. | In description static analysis | HOSTEDLOCAL | — | 2d ago |
| 68 | ReviewGate Code review against your team standards, before the pull request: generator finds, judge confirms | In description code review | HOSTEDLOCAL | — | 2d ago |
| 69 | Optibot AI code review for your AI assistant — review local changes, branch diffs, and patch files. | In description code review | HOSTEDLOCAL | — | 2d ago |
Ready-made AI agents
- $20/mo
- Cursor53$20/mo · free plan
- $10/mo · free plan
- $24/mo · free plan
- $20/mo
- $8/mo · free plan
Other use cases
FAQ
How many MCP servers are there for code review?
Electra Index lists 69 active MCP servers for code review from the Official MCP Registry. 30 offer a hosted endpoint and 54 publish their source code.
Is there a ready-made AI agent for code review instead?
Yes. If you prefer a finished product to plugging tools into your own assistant, Claude Code, Cursor and GitHub Copilot do this out of the box.
How this list is ordered: a tool comes first when the use case appears in its name rather than only in its description, then when it offers a hosted endpoint, then when its source code is public, then by how recently our robot saw it in the Official MCP Registry. The match to code Review comes from the publisher's description (keyword method), not from a test of the tool. Only active tools with a real description are listed. No tool pays to appear here.