$ loading_
Review GitHub PRs with AI and automate fix loops in coding tools.
This MCP tool is described as providing AI code review for GitHub PRs, connects to rami.reviews, and has code-execution capability; however, it comes from an official registry, is open source, and has been updated recently, with no clear red flags beyond its stated function. Overall it fits a caution rating rather than high risk, with primary attention on what code/PR data is sent out and the boundaries of local execution.
The materials indicate no separate keys or environment variables are required, and there is no explicit request for sensitive tokens; based on the available facts, credential exposure appears limited. Since it targets GitHub PR review, users should still consider whether existing host credentials could be used indirectly at runtime.
It is known to connect to the remote endpoint rami.reviews, and given its code-review function, it may send PR or code-related content to that service for processing. Connecting to a declared endpoint is a normal tool capability, but users should verify the scope of exported data, retention practices, and whether private code is included.
System checks show this tool has executes-code capability, and the description mentions an 'autofix loop,' suggesting it may trigger local commands or modification workflows. Such local execution is common for MCP tools, and the current materials do not show a clear mismatch with its stated purpose, but it should still be run in a constrained environment.
As a GitHub PR review/fix tool, it would normally need to read repository contents, diffs, and PR data, and may write back fixes or related files. Based on the available materials, there is no sign of data access far beyond what code review requires, but the missing README leaves the exact read/write scope insufficiently transparent.
The source is an official registry entry, with an open-source repository and updates within the last year, all of which are positive risk-reducing signals. However, the license is unspecified, the README is absent, and community stars are 0, limiting auditability and community validation. Overall the supply-chain posture is manageable but still warrants caution, not a high-risk rating by itself.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "Rami Code Review" MCP server from askskill: Run: claude mcp add --transport http 'reviews-rami-rami' 'https://rami.reviews/mcp'
Review this GitHub PR diff and identify potential bugs, maintainability issues, performance risks, and style inconsistencies. Prioritize findings by severity and suggest fixes.
A structured review with issue locations, risk explanations, priorities, and recommended fixes.
Based on the PR review findings, generate directly applicable code changes with minimal diffs and explain what each change fixes.
Applicable patches or revised code, along with explanations of the issues each change resolves.
Perform a pre-merge quality check on the current PR, focusing on test coverage, edge cases, error handling, and security concerns. Conclude whether it should be merged.
A merge recommendation, key risk list, and required tests or fixes before approval.
Automatically review GitHub PRs with efficient, deep analysis using static checks and LAG.
Review code, suggest refactors, and generate tests with AI assistance.
Connect GitHub repos and pull requests for faster code review.
Run multi-model code reviews to surface bugs, security risks, and improvements.
Query local codebases, guide safe changes, and produce audit-ready evidence.
Get intelligent, context-aware code reviews and improvement suggestions with MCP.