claude-gemini-mcp-slim

🥈Silver

Lightweight integration of Google's Gemini AI with Claude Code, offering 1M+ token context window, smart model selection, and code analysis tools for operations teams. Connects to existing workflows via Python, enhancing automation and code understanding.

225170Updated Today

Intermediate30min to implementautomation

Saves ~300 min per use

Quick InstallView Source

git clone https://github.com/cmdaltctr/claude-gemini-mcp-slim.git

Works with:

Claude

Overview

About This Skill

How to Use

[{"step":"Install claude-gemini-mcp-slim via pip: `pip install claude-gemini-mcp-slim` and configure your Google API key in `.env`.","tip":"Use `export GOOGLE_API_KEY=your_key_here` for temporary testing or add to your shell profile for persistence."},{"step":"Run a targeted analysis by pasting the prompt template into your Claude/ChatGPT interface, replacing [PLACEHOLDERS] with your specific context (e.g., codebase path, issue type).","tip":"For large codebases (>1M tokens), split the analysis into modules (e.g., `/services/auth`) to avoid hitting token limits."},{"step":"Review the output, focusing on the prioritized list of issues. Use the provided code snippets to implement fixes or adapt them to your tech stack.","tip":"For security-critical issues (e.g., hardcoded secrets), address them immediately before proceeding with other fixes."},{"step":"Integrate the claude-gemini-mcp-slim into your CI/CD pipeline using the provided pre-commit hook or a custom GitHub Action to scan code on every push.","tip":"Example GitHub Action:\n```yaml\nname: Code Analysis\non: [push]\njobs:\n analyze:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v4\n - run: pip install claude-gemini-mcp-slim\n - run: claude-gemini analyze --path ./src --issue memory_leaks\n```"},{"step":"Monitor the impact of fixes using your existing observability tools (e.g., Prometheus, Datadog). Re-run the analysis weekly to catch regressions.","tip":"Set up a cron job to run the analysis during off-peak hours to avoid performance impact on your systems."}]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/cmdaltctr/claude-gemini-mcp-slim

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use the claude-gemini-mcp-slim integration to analyze [CODEBASE_PATH] for [SPECIFIC_ISSUE]. Focus on identifying [TECHNICAL_DETAILS] such as memory leaks, inefficient algorithms, or security vulnerabilities. Provide a prioritized list of fixes with estimated effort in hours and potential impact. Include code snippets for critical issues. If possible, suggest automated remediation steps using [TOOL_NAME] or [SCRIPT_LANGUAGE].

Example Output

Analyzing the `/backend/services` codebase for memory leaks in the user authentication module (v2.4.1). The scan identified 3 critical issues:

1. **Memory Leak in JWT Token Cache**
   - Location: `/services/auth/cache.py:45-52`
   - Issue: Tokens are stored in a global dictionary without TTL expiration, causing 1.2GB memory growth over 7 days in production (observed in monitoring dashboard).
   - Impact: High - leads to OOM errors during peak traffic (500 errors increased by 18% this week).
   - Fix: Replace global dict with `functools.lru_cache(maxsize=10000)` with 15-minute TTL. Estimated effort: 2 hours.
   - Code snippet:
     ```python
     # BEFORE
     token_cache = {}
     
     # AFTER
     from functools import lru_cache
     from datetime import datetime, timedelta
     
     @lru_cache(maxsize=10000)
     def get_cached_token(token_id):
         return token_cache.get(token_id)
     ```

2. **Inefficient SQL Query in User Lookup**
   - Location: `/services/db/users.py:89-95`
   - Issue: Full table scan on `users` table (12M rows) due to missing index on `email` column. Query time increased from 45ms to 2.1s after recent data growth.
   - Impact: Medium - degrades login API response time by 400ms (P95 latency).
   - Fix: Add index `CREATE INDEX idx_users_email ON users(email)`. Estimated effort: 1 hour.

3. **Hardcoded API Keys**
   - Location: `/config/secrets.env:3`
   - Issue: Stripe API key exposed in version control. Detected via `git-secrets` scan.
   - Impact: Critical - potential financial fraud if key is compromised.
   - Fix: Rotate key immediately and use environment variables. Estimated effort: 30 minutes.

Automated remediation: Created a pre-commit hook using `pre-commit` framework to validate no secrets are committed. Hook script:
```yaml
repos:
  - repo: https://github.com/Yelp/detect-secrets
    rev: v1.4.0
    hooks:
      - id: detect-secrets
        args: ['--baseline', '.secrets.baseline']
```

Total estimated remediation time: 3.5 hours. After fixes, memory usage should stabilize at ~200MB (down from current 1.4GB), and login API latency should return to baseline.