Skip to main content
Glama
Sign In
infra-mcp

infra-mcp

by DTG404
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

infra-mcp

MCP server that gives Claude Code real-time visibility into local infrastructure — Docker containers and system health.

Tools

System (8 tools)

Tool

Description

system_overview

CPU load, memory, uptime

gpu_status

NVIDIA GPU utilization and VRAM

gpu_processes

Processes using the GPU

disk_usage

Filesystem usage

io_pressure

PSI metrics for I/O pressure

top_processes

Top processes by CPU/memory

service_status

systemd service status

memory_detail

Detailed memory breakdown

Docker (7 tools)

Tool

Description

list_containers

List all containers with status

inspect_container

Detailed container info

container_logs

Tail container logs

start_container

Start a stopped container

stop_container

Stop a running container

restart_container

Restart a container

compose_status

Docker Compose project status

Related MCP server: SafeFlo

Setup

npm install

Usage

npm start

Configure in Claude Code MCP settings:

{
  "mcpServers": {
    "infra": {
      "command": "node",
      "args": ["/path/to/infra-mcp/index.js"]
    }
  }
}

Configuration

Env Variable

Default

Description

DOCKER_HOST

/var/run/docker.sock

Docker socket path

NVIDIA_SMI_PATH

nvidia-smi

Path to nvidia-smi binary

Tech Stack

  • Node.js (>=18)

  • @modelcontextprotocol/sdk

  • Docker API v1.43 (Unix socket)

  • /proc filesystem for system metrics

  • nvidia-smi for GPU monitoring

Available Tools

21 tools
compose_statusA

Show Docker Compose projects with their containers grouped by project

Inputs: format.

container_healthC

Show Docker container health check status

Inputs: format.

container_logsB

Tail logs from a Docker container

Inputs: id (required), tail, since, format.

disk_usageA

Disk usage per mount point (excludes tmpfs, devtmpfs, efivarfs)

Inputs: format.

docker_statsA

Show one-shot Docker stats for running containers

Inputs: format.

gpu_processesA

List processes currently using NVIDIA GPU VRAM

Inputs: format.

gpu_statusA

NVIDIA GPU status: name, temperature, utilization, VRAM usage

Inputs: format.

inspect_containerC

Full inspect details for a Docker container

Inputs: id (required), format.

io_pressureA

PSI (Pressure Stall Information) for CPU, memory, and I/O — shows if the system is under real stress

Inputs: format.

list_containersB

List Docker containers with optional filters

Inputs: all, format, name_filter, label_filter.

list_imagesA

List Docker images with optional all filter

Inputs: all, format.

list_networksA

List Docker networks with IPAM info

Inputs: format.

list_volumesA

List Docker volumes and warnings

Inputs: format.

memory_detailA

Full /proc/meminfo breakdown with human-readable sizes

Inputs: format.

prune_systemC

Show or perform Docker system prune summaries

Inputs: format, dry_run.

restart_containerC

Restart a Docker container

Inputs: id (required), format.

service_statusA

Check systemd service status (system or user unit)

Inputs: service (required), user, format.

start_containerA

Start a stopped Docker container

Inputs: id (required), format.

stop_containerB

Stop a running Docker container with optional timeout

Inputs: id (required), format, timeout.

system_overviewA

One-shot system health check: CPU load averages, memory usage, swap, and uptime

Inputs: format.

top_processesA

Top N processes sorted by CPU or memory usage

Inputs: count, format, sort_by.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.2/5.0

    Scored across 21 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: system monitoring tools target different metrics, and Docker tools separate list/inspect/logs/start/stop/restart. Minor overlap exists between list_containers and compose_status (both list containers but with different grouping) and between container_health and inspect_container (health info is a subset of inspect), but descriptions help differentiate them.

    Naming Consistency3/5

    The naming is mixed: system and GPU tools use noun_noun patterns (system_overview, gpu_status, disk_usage), while Docker tools use verb_noun patterns (list_containers, start_container, restart_container). This inconsistency is mildly confusing, though the pattern is predictable within each subdomain, and all names are readable.

    Tool Count4/5

    21 tools is on the higher end of the optimal range, but each tool covers a specific monitoring or Docker management function that justifies its presence. The count is appropriate for a server that spans both system health and container operations, without feeling bloated.

    Completeness3/5

    The server covers system monitoring and Docker container lifecycle well, but has notable gaps: no service management (only status), no Docker container create/remove, no image pull/remove, and no volume/network creation. Basic operations are covered, but full infrastructure management is incomplete.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers