Selvage is a CLI tool that automates code reviews by using AI to analyze Git diffs, improving code quality and identifying bugs and security vulnerabilities.
From the registry: An LLM-based code review MCP server with AST-powered smart context extraction
Please install the `selvage` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Required runtime
Optional prerequisites:
- OpenRouter API key (or provider-specific key) — Required for AI-powered code reviews. Not needed when using get_review_context (agent-delegated mode). (https://openrouter.ai)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["selvage","mcp"]
- optional environment variables:
- `OPENROUTER_API_KEY`: OpenRouter API key for AI model access. Not required when using agent-delegated review (get_review_context tool). (example: `<your-openrouter-api-key>`)
- `ANTHROPIC_API_KEY`: Anthropic API key (alternative to OpenRouter) (example: `<your-anthropic-api-key>`)
- `OPENAI_API_KEY`: OpenAI API key (alternative to OpenRouter) (example: `<your-openai-api-key>`)
Note: AI code review tool using Git diffs. Tree-sitter AST analysis for smart context extraction. 'get_review_context' tool lets host agent (Claude Code) do reviews without an API key.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPENROUTER_API_KEYrequiredAPI key for accessing OpenRouter services.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Validate oh-my-posh configurations and segment snippets against the official schema.
Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.