Code Review Analyst MCP Server

Gemini-powered MCP server for pull request analysis with structured outputs for findings, release risk, and focused patch suggestions.

Overview

This server accepts unified diffs and returns structured JSON results — findings with severity, impact categories, merge risk, test plans, and verbatim search/replace fixes. It uses Gemini Thinking models (Flash for fast tools, Flash for deep analysis) and runs over stdio transport.

Key Features

• Impact Analysis — Objective severity scoring, breaking change detection, and rollback complexity assessment.
• Review Summary — Concise PR digest with merge recommendation and change statistics.
• Deep Code Inspection — Flash model with high thinking level for context-aware analysis using full file contents.
• Search & Replace Fixes — Verbatim, copy-paste-ready code fixes tied to specific findings.
• Test Plan Generation — Systematic test case generation with priority ranking and pseudocode.
• Async Task Support — All tools support MCP task lifecycle with progress notifications.

Requirements

• Node.js >=24
• One API key: GEMINI_API_KEY or GOOGLE_API_KEY
• MCP client that supports stdio servers and tool calls

Quick Start

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Client Configuration

{
  "servers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

code --add-mcp '{"name":"code-review-analyst","command":"npx","args":["-y","@j0hanz/code-review-analyst-mcp@latest"]}'

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

claude mcp add code-review-analyst -- npx -y @j0hanz/code-review-analyst-mcp@latest

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

amp mcp add code-review-analyst -- npx -y @j0hanz/code-review-analyst-mcp@latest

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "npx",
      "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
      "env": {
        "GEMINI_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

{
  "context_servers": {
    "code-review-analyst": {
      "command": {
        "path": "npx",
        "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
        "env": {
          "GEMINI_API_KEY": "YOUR_API_KEY"
        }
      }
    }
  }
}

{
  "augment.advanced": {
    "mcpServers": [
      {
        "name": "code-review-analyst",
        "command": "npx",
        "args": ["-y", "@j0hanz/code-review-analyst-mcp@latest"],
        "env": {
          "GEMINI_API_KEY": "YOUR_API_KEY"
        }
      }
    ]
  }
}

{
  "mcpServers": {
    "code-review-analyst": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GEMINI_API_KEY=YOUR_API_KEY",
        "ghcr.io/j0hanz/code-review-analyst-mcp:latest"
      ]
    }
  }
}

docker build -t code-review-analyst-mcp .

Tools

[!IMPORTANT]
Call generate_diff first (mode: "unstaged" or "staged"). All review tools read the cached server-side diff (diff://current) and do not accept a direct diff parameter.

generate_diff

Generate and cache the current branch diff for downstream review tools.

Returns: diffRef, stats (files, added, deleted), generatedAt, mode, message.

analyze_pr_impact

Assess the impact and risk of cached pull request changes using the Flash model.

Returns: severity (low/medium/high/critical), categories[], breakingChanges[], affectedAreas[], rollbackComplexity, summary.

generate_review_summary

Summarize a pull request diff and assess high-level risk using the Flash model.

Returns: summary, overallRisk (low/medium/high), keyChanges[], recommendation, stats (filesChanged, linesAdded, linesRemoved).

inspect_code_quality

Deep-dive code review using the Flash model with high thinking (16K token budget).

Returns: summary, overallRisk (low/medium/high/critical), findings[] (severity, file, line, title, explanation, recommendation), testsNeeded[], contextualInsights[].

[!NOTE]
Diff size bounded by MAX_DIFF_CHARS (default 120,000). Expect 60-120s latency due to deep thinking.

suggest_search_replace

Generate verbatim search-and-replace blocks to fix a specific finding using the Flash model with high thinking.

Returns: summary, blocks[] (file, search, replace, explanation), validationChecklist[].

generate_test_plan

Create a test plan covering the changes in the diff using the Flash model with thinking (8K token budget).

Returns: summary, testCases[] (name, type, file, description, pseudoCode, priority), coverageSummary.

Resources

Prompts

Configuration

CLI Arguments

Environment Variables

Models

Workflows

Quick PR Triage

1. Call analyze_pr_impact to get severity and category breakdown.
2. If low/medium — call generate_review_summary for a quick digest.
3. If high/critical — proceed to deep inspection.

Deep Code Inspection

1. Call inspect_code_quality with the cached diff.
2. Use focusAreas to target specific concerns (security, performance).
3. Review findings and contextualInsights.

Remediation & Testing

1. For each finding, call suggest_search_replace with findingTitle and findingDetails.
2. Call generate_test_plan to create a verification strategy.
3. Apply fixes and implement tests.

Development

npm ci            # Install dependencies
npm run dev       # TypeScript watch mode
npm run dev:run   # Run built server with .env and --watch

Debugging with MCP Inspector

npx @modelcontextprotocol/inspector node dist/index.js

Build & Release

Releases are triggered via GitHub Actions workflow_dispatch with version bump selection (patch/minor/major/custom).

The pipeline runs lint, type-check, test, and build, then publishes to three targets in parallel:

• npm — @j0hanz/code-review-analyst-mcp with OIDC trusted publishing and provenance
• Docker — ghcr.io/j0hanz/code-review-analyst-mcp (linux/amd64, linux/arm64)
• MCP Registry — io.github.j0hanz/code-review-analyst

Troubleshooting

License

MIT