Skip to main content
Glama
Madiocre

DevEnv Doctor MCP

by Madiocre
README.md
# devenv-doctor-mcp

An MCP server that gives an LLM client (Claude, or any MCP-compatible host) the ability to actually inspect your local dev environment — Docker container health, pnpm workspace integrity, and stuck/hung processes — instead of you copy-pasting terminal output back and forth.

**Now powered by [NitroStack](https://nitrostack.com)!** The project has been refactored from a monolithic script into a clean, declarative architecture using `@nitrostack/core`. 

## Why this exists

While building this, I hit a real pnpm bug: `pnpm self-update` corrupted my global environment lockfile, and every single `pnpm` invocation started crashing with `Cannot use 'in' operator to search for 'integrity' in undefined`. Diagnosing it meant manually hunting through `~/.local/share/pnpm`, checking process states, and re-running commands with debug flags — exactly the kind of repetitive, mechanical diagnosis an LLM with the right tools could do directly. This project is that toolset.

## What it does

The application provides four primary tools, registered via `@Tool` decorators:

*   **`ping`**: Sanity check — returns pong plus the current server time.
*   **`check_docker_status`**: Checks whether a given container is running and whether its expected port is actually bound on the host. It reports the current state, healthcheck status, and every configured port mapping.
*   **`check_pnpm_workspace`**: Validates `pnpm-workspace.yaml`, detects orphaned packages, dead glob patterns, lockfile staleness, and missing package manager pin. 
*   **`diagnose_stuck_process`**: Finds processes bound to a given port and flags likely zombie/hung states.

---

## 🚀 Quick Start Guide & Usage

Because this project is now built with NitroStack, it natively bootstraps an HTTP server using the `@McpApp` decorator.

### 1. Setup & Build
```bash
npm install
npm run build
```

### 2. Start the Server
Start the application. By default, NitroStack will bind the MCP `HTTP` transport to `port` 3000, unless you provide a PORT environment variable:  
```bash
PORT=8080
node build/main.js
```

### 3. Testing with the MCP Inspector
Since the server now runs over `HTTP` rather than standard I/O, you can connect the official Inspector using the SSE (Server-Sent Events) URL:
```bash
npx @modelcontextprotocol/inspector http://localhost:3000/sse
```

_Note: Depending on your exact NitroStack configuration, the SSE endpoint path may vary. Check your console output upon startup._

### 4. Connecting to a Host (e.g., Claude Desktop)
To use this with Claude Desktop, you can point it to the executable script using standard configuration. If your host requires standard I/O (stdio) instead of `HTTP`, you may need to adjust the transport configuration in src/main.ts from type: "http" to type: "stdio"

## Known limitations
Being upfront about these rather than letting them surprise you:
- Glob matching doesn't support negation patterns (!**/test/**), which some pnpm-workspace.yaml files use to exclude folders. A workspace using negation may get spurious "dead pattern" warnings.
- Lockfile staleness is a mtime heuristic, and git clone resets file mtimes to roughly the same moment — so this check can false-positive immediately after a fresh clone, even on a perfectly healthy workspace.  - `ps` flags used in `diagnose_stuck_process` are GNU/Linux-specific (--no-headers); this tool hasn't been tested on macOS/BSD ps.  
- Stuck-process detection is a single snapshot, not a trend — a process briefly in uninterruptible-sleep (D) state doing normal disk I/O can be flagged even though it's healthy. A more robust version would sample twice with a delay before flagging.

_None of these are silent — each one is either surfaced as a message from the tool itself, or documented here._

## Built With
- @nitrostack/core for declarative MCP routing, dependency injection, and application bootstrapping
- `zod` for strict input schema validation
- `yaml` for real YAML parsing.
- Node's `child_process.execFile` throughout (never exec) — every shell call uses array arguments, not interpolated strings, so user-supplied input (container names, paths) can't be used for shell injection.

## License
**MIT**

TDQS

A3.6/5.0

Scored across 4 tools

Disambiguation5/5

Each tool targets a distinct concern: ping for liveness, Docker container status, pnpm workspace validation, and process diagnosis. No two tools overlap in purpose, so an agent can easily select the right one.

Naming Consistency4/5

Three tools use a verb_noun pattern (check_docker_status, check_pnpm_workspace, diagnose_stuck_process), but 'ping' deviates by using a standalone verb without a prefix. This is a minor inconsistency, but the naming remains intuitive.

Tool Count5/5

With only 4 tools, the server is tightly scoped for a development environment diagnostics tool. Each tool provides a specific health check, and the count feels appropriate without being too thin or overloaded.

Completeness3/5

The tools cover several common dev environment issues (Docker, pnpm, stuck processes), but the broad 'DevEnv Doctor' purpose suggests missing checks like system resource monitoring or package manager version validation. These are notable gaps but agents can work around them.

Maintenance

ActivityStale
ResponsivenessNo issues