Grumpy Senior Developer as MCP server

@sinedied

Repository Homepage

Basic information

About Grumpy Senior Developer as MCP server

Let the grumpy senior dev review your code with this MCP server

#nodejs #mcp #llm #generative-ai #model-context-protocol #genaiscript

Grumpy Senior Developer as MCP server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "grumpydev-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}

Grumpy Senior Developer as MCP server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Grumpy Senior Developer as MCP server?

This MCP server provides automated code reviews delivered with the sarcastic, cynical tone of a grumpy senior developer. It is designed for developers who want to review pull requests or get critical feedback on code, offering the same perspective as a seasoned (and grumpy) team member.

How to use Grumpy Senior Developer as MCP server?

Requires Node.js 20+. You can install it for GitHub Copilot in VS Code or VS Code Insiders via the provided install links, command line (code --add-mcp or code-insiders --add-mcp), or by adding it manually to .vscode/mcp.json. For Claude desktop, add it to claude_desktop_config.json. To test, use MCP Inspector with npx -y grumpydev-mcp as the command and arguments. Optionally set the model via the GENAISCRIPT_DEFAULT_MODEL environment variable.

Key features of Grumpy Senior Developer as MCP server

Delivers code reviews with a sarcastic, cynical tone.
Identifies issues and suggests fixes in a blunt manner.
Works with GitHub Copilot and Claude Desktop.
Configurable model backend via GenAIScript.
Runs locally via stdio transport after npx execution.

Use cases of Grumpy Senior Developer as MCP server

Review code in pull requests before merging.
Get quick, opinionated feedback on code snippets.
Provide a lighter, entertaining alternative to conventional linting.
Use as a teaching tool to highlight common mistakes.

Frequently asked questions

What is Model Context Protocol (MCP)?

MCP is an open protocol that standardizes how applications provide context to LLMs, like a USB-C port for AI applications. It provides a standardized way to connect AI models to different data sources and tools.

What runtime dependencies are required?

Node.js 20+ must be installed on your system. The server is run via `npx -y grumpydev-mcp` without additional installation steps.

How can I configure the model used?

Set the `GENAISCRIPT_DEFAULT_MODEL` environment variable with a provider and model name (e.g., `github:gpt-4o`). Default is GitHub Models with GPT-4o. See GenAIScript documentation for supported providers and additional configuration.

Is my code sent to an external service?

The server runs locally via stdio transport. While the model inference may use external AI services (depending on your model configuration), the code is processed locally before being sent to the model.

What transports and authentication does it support?

The server uses stdio transport. No built-in authentication; it is designed for local use with tools like VS Code and Claude Desktop.

Comments

More Developer Tools MCP servers

Ramen

bkraad47

Multi-zone MCP server for GKE/EKS/AKS: Python tools from git, NeMo guardrails, SSO, autoscaling.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

TranscriptFetch MCP Server

TranscriptFetch

Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.