mcp-heimdall
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| system_infoA | Get OS and architecture details. |
| inspect_runtimesA | Check Node, Python version and config. |
| audit_dependenciesC | Check for missing packages. |
| audit_envA | Check .env file against template. |
| suggest_correctionsB | Run all diagnostics and get prioritized fix suggestions. |
| list_portsA | List all active listening ports and their processes. |
| kill_port_processB | Kill the process running on a specific port. |
| inspect_dockerA | Check Docker daemon status and list containers. |
| check_connectivityB | Test internet connection to essential dev services. |
| project_doctorC | Scan for NPM vulnerabilities and outdated packages. |
| resource_watcherB | Monitor CPU load, memory and disk usage. |
| workspace_janitorC | Find large files and temporary directories for cleanup. |
| path_inspectorA | Inspect system PATH and critical dev tools versions. |
| process_explorerB | Identify top resource-consuming and orphan processes. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool addresses a distinct aspect of system health: auditing dependencies, environment, connectivity, Docker, runtimes, processes, ports, PATH, resource usage, vulnerabilities, and cleanup. No two tools overlap in purpose; even related tools like 'list_ports' and 'kill_port_process' are clearly separated.
Most tools follow a verb_noun or descriptive pattern (e.g., audit_dependencies, check_connectivity, kill_port_process). However, some use noun_noun (path_inspector, process_explorer, resource_watcher) which introduces minor inconsistency but remains readable and predictable.
With 14 tools covering diagnostics, inspection, and maintenance actions, the count is well-scoped for a system health server. Each tool earns its place, and the number is within the ideal 3-15 range.
The server covers a comprehensive set of system checks: OS, processes, ports, Docker, runtimes, dependencies, environment, connectivity, resource usage, vulnerabilities, and disk cleanup. The inclusion of 'suggest_corrections' that runs all diagnostics and gives prioritized fixes rounds out the surface with no obvious gaps.