About heimdall
heimdall is an environment diagnostics and repair-suggestion MCP server for AI agents. It checks runtimes, dependencies, system resources, and project configuration, then consolidates prioritized fixes.
Key features
- 01Check system and runtime versions
- 02Audit PATH and development tools
- 03Scan dependencies and .env files
- 04Monitor processes, resources, and ports
- 05Check Docker and connectivity
- 06Consolidate environment fixes
Use cases
- 01Troubleshoot project environment issues
- 02Find large files and temporary directories
- 03Inspect occupied ports and orphan processes
MCP support
It exposes system, project, and environment diagnostic tools to MCP clients, including tools that suggest corrections.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y @lchampz/mcp-heimdallDEBUGEnable debug logging (true/false)Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
5Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project README🛡️ MCP Heimdall
Advanced Environment Architect & Diagnostic Tool for Model Context Protocol (MCP).
Heimdall helps AI agents understand, verify, and fix their execution environment. It provides detailed insights into system architecture, runtime versions, dependencies, and environment variables, along with actionable correction suggestions.
✨ Features
- Workspace Janitor: Find large files (>50MB) and temporary directories (
dist,build, etc.) for cleanup. - Path Inspector: Audit the
PATHvariable and verify versions of critical dev tools (git,brew,make). - Process Explorer: Identify top CPU/Memory consumers and potential orphan Node/Python processes.
- Docker Sight: Check Docker daemon status, list containers and images.
- Connectivity Check: Ping essential services (GitHub, NPM, Docker Hub) to verify internet status.
- Project Doctor: Scan Project for NPM vulnerabilities and outdated packages.
- Resource Watcher: Monitor CPU load, memory usage, and disk space.
- Port Manager: List active listening ports and kill processes blocking specific ports.
- Runtime Inspector: Verify Node.js, Python, Java, and Kotlin versions against project requirements.
- Dependency Guard: detects missing
node_modulesor virtual environments. - Environment Audit: Compares
.envagainst templates and flags missing keys. - Intelligent Advisor: consolidated tool that suggests specific commands to fix environment issues.
🛠️ Tools
| Tool | Description |
|---|---|
system_info | Get OS and architecture details. |
inspect_runtimes | Check Node, Python, Java, and Kotlin versions. |
inspect_docker | Check Docker daemon status and list containers. |
check_connectivity | Test internet connection to essential dev services. |
project_doctor | Scan for NPM vulnerabilities and outdated packages. |
resource_watcher | Monitor CPU load, memory and disk usage. |
workspace_janitor | Find large files and temporary directories for cleanup. |
path_inspector | Inspect system PATH and critical dev tools versions. |
process_explorer | Identify top resource-consuming and orphan processes. |
audit_dependencies | Detect missing packages or broken environments. |
audit_env | Verify .env files against templates. |
list_ports | List all active listening ports and their processes. |
kill_port_process | Kill the process running on a specific port. |
suggest_corrections | The Core Feature: Runs all checks and returns prioritized solutions. |
🚀 Installation
Quick Integration
Run this command to automatically configure Heimdall in your current workspace:
npx @lchampz/mcp-heimdall integrate
This will create a .vscode/mcp.json file with the correct configuration.
For Users (via MCP Registry)
Add to your mcp.json or editor settings:
{
"servers": {
"heimdall": {
"command": "node",
"args": ["path/to/mcp-heimdall/build/index.js"]
}
}
}
For Developers
- Clone the repository
- Install dependencies:
npm install - Build the project:
npm run build - Run in dev mode:
npm run dev
📄 License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.