infra-mcp
Lists Grafana dashboards and data sources, creates dashboards from a simple list, and imports community dashboards by ID using a service-account token.
Supported through the generic REST connector for configured REST API interactions with Graylog.
Supported through the generic REST connector for configured REST API interactions with Jira.
Runs PromQL queries and retrieves down targets and firing alerts from Prometheus.
Supported through the generic REST connector for configured REST API interactions with Veeam.
Provides tools for VMware vCenter/ESXi environments: VMs, hosts, host hardware sensors, clusters, datastores, alarms, old snapshots, and power actions when write mode is enabled.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
infra-mcp
\*\*Status: v0.1.0.\*\* Tested against simulators (VMware vcsim and a Redfish mock server). Real-hardware pilots are welcome: please open an issue with your results.
One MCP server that lets AI assistants (Claude, ChatGPT, Cursor, etc.) safely work with your IT infrastructure. One MCP server that lets AI assistants (Claude, ChatGPT, Cursor, etc.) safely work with your IT infrastructure.
Safe by default: read-only mode, every call is audit-logged, secrets are redacted, host allowlists.
Works anywhere: Windows, Linux, macOS, Docker. Credentials come from environment variables, never from code.
Modular: enable only the connectors you need. Add a new one by dropping in one file.
Connector | What it does | Credentials |
| ping, DNS, port check, TLS certificate expiry | none |
| physical server health via BMC (iDRAC/iLO/CIMC/XCC): CPU, memory, temps, fans, PSUs, disks, event log, fleet check | read-only BMC account |
| VMs, hosts, host hardware sensors, clusters, datastores, alarms, old snapshots, power actions (write) | vCenter/ESXi user |
| PromQL queries, down targets, firing alerts | URL (+ token) |
| list dashboards/data sources, create dashboards from a simple list, import community dashboards by ID | service-account token |
| uptime, disks, stopped services, pending reboot, event errors (WinRM) | service account |
| any tool with a REST API (ServiceNow, Jira, Graylog, Veeam...) via config only | per service |
Quick start (5 minutes)
git clone https://github.com/EsayAbhi/infra-mcp.git
cd infra-mcp
python -m venv .venv
# Windows: .venv\\\\Scripts\\\\activate Linux/macOS: source .venv/bin/activate
pip install -e . # add ".\\\[windows]" for the Windows connector
cp config.example.yaml config.yaml # Windows: copy config.example.yaml config.yaml
cp .env.example .env # put your passwords here
infra-mcp --check # validates config and lists toolsEnable the connectors you want in config.yaml (enabled: true).
Related MCP server: VMware-Monitor
Daily health report
One report that merges hardware (Redfish), VMware (hosts, sensors, datastores, alarms, old snapshots) and certificate expiry, critical problems first.
Ask your AI: "Give me the daily infrastructure health report."
Or run it yourself:
infra-mcp --config config.yaml --report --output report.md --emailSchedule it every morning with Windows Task Scheduler or cron. Exit code:
0OK,1warnings,2critical.Thresholds (datastore free %, snapshot age, certificate days) are configurable in
config.yaml.
Sample output
Demo environment (simulators), not real servers. Demo thresholds are set so even brand-new snapshots are flagged.

A power action is refused while read_only is true:

Every call is recorded in an audit log, with secrets hidden:

Connect to Claude Desktop
Edit claude\\\_desktop\\\_config.json (Settings > Developer > Edit Config):
{
"mcpServers": {
"infra": {
"command": "C:\\\\\\\\path\\\\\\\\to\\\\\\\\infra-mcp\\\\\\\\.venv\\\\\\\\Scripts\\\\\\\\infra-mcp.exe",
"args": \\\["--config", "C:\\\\\\\\path\\\\\\\\to\\\\\\\\infra-mcp\\\\\\\\config.yaml"]
}
}
}Restart Claude Desktop, then ask: "Which datastores are below 15% free?" or "Check disks on SRV-APP01."
Remote / team use (Docker)
docker build -t infra-mcp .
docker run -p 8000:8000 -v $(pwd)/config.yaml:/config/config.yaml --env-file .env infra-mcpPut it behind your own reverse proxy with authentication before exposing it beyond localhost.
Safety model
read\\\_only: true(default) blocks every action that changes something, in every connector.To allow changes, set
read\\\_only: falseand use accounts with least privilege.audit.jsonlrecords who/what/when for every call. Passwords and tokens are masked.Use
allowed\\\_hostsinnetworkandwindowsto limit where the AI can reach.Use a dedicated read-only service account per system.
Add your own connector
Copy
src/infra\\\_mcp/connectors/\\\_template.pytoconnectors/yourtool.py.Set
NAME, write tools insideregister():
@guard.tool(mcp) # read tool
def yourtool\\\_status() -> dict:
"""The AI reads this docstring to know when to use the tool."""
@guard.tool(mcp, write=True) # blocked in read-only mode
def yourtool\\\_restart(name: str) -> dict: ...Add a block under
connectors:inconfig.yaml. No other file changes needed.
For tools with a plain REST API you do not even need code: add them under rest: in config.yaml.
Development and testing
pip install -e ".\\\[dev]"
pytest # unit and simulator tests
python scripts/run\\\_all\\\_checks.py # full check with fake VMware + hardware servers (needs vcsim)License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Infrastructure context for any AI: VMware, Nutanix, Kubernetes and cloud. Read-only, off production.
Let AI operate servers without SSH. Choose actions, approve risky changes, and audit every step.
Read-only Linux server and Docker monitoring for AI assistants: CPU, memory, disk, network.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
Related MCP Servers
- AlicenseAqualityAmaintenanceAI-powered VMware vCenter/ESXi monitoring and operations. 20 MCP tools for inventory queries, health monitoring, VM lifecycle management, fast provisioning (Linked Clone, OVA, template deploy), snapshot management, and datastore browsing. Supports vSphere 6.5–8.0. Works with local models via Ollama/LM Studio.44617 PyPI87MIT
- AlicenseAqualityBmaintenanceRead-only VMware vCenter/ESXi monitoring. 8 MCP tools for VM inventory, host status, datastore capacity, cluster info, alarms, events, and VM details. Code-level enforced safety — no destructive operations exist in the codebase. Supports vSphere 6.5–8.0. Works with local models via Ollama/LM Studio.33506 PyPI18MIT
- AlicenseBqualityBmaintenanceEnables AI assistants to perform comprehensive read-only diagnostics of VMware ESXi hosts, covering CPU Ready, disk latency, snapshots, datastore usage, hardware health, events, and performance history. It guarantees no write operations, helping users identify bottlenecks and infrastructure issues safely.1338 PyPIMIT
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to query servers, uptime monitors, incidents, DNS, domains, certificates, and audit logs in plain language, with limited on-call actions when permitted.Apache 2.0