Code review against the rules your team actually wrote, not generic best practice. A cheap generator finds problems, an independent judge refutes them against full files, so the noise stays down. Two tools for the agent loop (getteamrules, reviewchanges), plus a pre-push gate and a bot on GitLab/GitHub pull requests. Single binary, no Node or Docker; bring your own model key.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
AI code review by your team's standards β in the editor while the agent works, at the pre-push hook, and again on the pull request.
Free. Self-hosted. Bring your own model key: the code never leaves your infrastructure, and nothing is reported back to the vendor.
This repository distributes the releases. The source is not published; the binaries below are the same artifacts served from the site.
A general-purpose model tells you about SQL injection in the abstract. ReviewGate reads the
agreements your team actually wrote β the ADRs, the conventions, the rules in
.reviewgate/config.yml β and reports the places where this change breaks them. A finding
that quotes your own rule is one a reviewer can act on; a finding that quotes a textbook is
one they scroll past.
The review runs in three places, on the same rules and the same judge:
| Where | What it does |
|---|---|
| CLI | reviewgate review over staged, uncommitted or committed changes |
| Pre-push hook | refuses a git push that carries blocking findings |
| MCP server | the coding agent calls the review itself, before the request exists |
| Bot on GitLab / GitHub | summary, inline findings, one-click fixes, a gate on the merge |
Two passes under the hood: a cheap generator looks for problems, a stronger judge refutes them against the code, and only what survives is published. That is what keeps the noise down β the numbers behind it are on the site.
Download the archive for your platform from
the latest release, unpack, put
it on your PATH:
Platforms: darwin-arm64, darwin-x64, linux-x64, linux-x64-musl, linux-arm64,
win-x64. Checksums are published with every release as SHA256SUMS.
The same files are served from the site β https://reviewgate.dev/docs/agents lists every platform with its download command β use whichever is faster for you.
Two commands wire everything at once: the MCP tools (get_team_rules,
review_changes), a pre-push review gate, and the skills that make the agent
review its changes before calling work done. The plugin needs the CLI binary
from the section above.
Or from the shell: claude plugin marketplace add ReviewGate/reviewgate,
then claude plugin install reviewgate@reviewgate.
The image is registry.reviewgate.dev/reviewgate-bot, mirrored on Docker Hub as
novohudonossor/reviewgate-bot. Full walkthrough, webhook setup and the list of environment
variables: https://reviewgate.dev/docs/install
Nowhere. The bot and the CLI talk to the model provider you configured, on your key, from your network. There is no telemetry, no call home and no vendor account. Review metadata β counts, severities, tokens spent β stays in your own database, and source code is never written to logs or to disk.
How that is arranged, and how to verify it yourself: https://reviewgate.dev/security
The product is free and stays free. If it earns its place in your pipeline, the most useful thing you can do is use it and tell a colleague: https://reviewgate.dev/donate
Questions and feedback: @ReviewGate on Telegram.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/reviewgate-reviewgate)<a href="https://allmcps.com/mcp/reviewgate-reviewgate"><img src="https://allmcps.com/api/badge/reviewgate-reviewgate?style=directory" alt="Reviewgate on AllMCPs" /></a>