PodWarden
MCP Integration

MCP Integration

Connect AI assistants to PodWarden using the Model Context Protocol

PodWarden includes a built-in MCP (Model Context Protocol) server that lets AI assistants manage your infrastructure through natural language.

What is MCP?

MCP is an open standard that lets AI applications (like Claude Desktop, Claude Code, and Cursor) call tools exposed by external services. PodWarden exposes 115 tools covering clusters, hosts, workloads, deployments, storage, ingress, secrets, and system configuration.

Two ways to connect

Direct connection

Your AI client connects directly to your PodWarden instance's /mcp endpoint using a pwm_ token. Best when your instance is reachable from wherever your AI client runs.

Hub proxy (recommended)

Your AI client connects to PodWarden Hub's MCP endpoint. Hub routes tool calls to your instance through a secure WebSocket tunnel. No ports to open, no VPN to set up.

Why use Hub proxy?

  • No need to expose your PodWarden instance to the internet
  • Works behind NAT, firewalls, and VPNs — the tunnel is outbound
  • Manage multiple instances from a single MCP endpoint
  • All tool calls are logged in PodWarden's audit trail

What you can do

With MCP connected, you can ask your AI assistant things like:

  • "List all my clusters and their status"
  • "Show me hosts with available GPUs"
  • "Create a stack for llama.cpp with 2 GPUs"
  • "Deploy the staging workload to the prod cluster"
  • "What's wrong with the failing deployment?"
  • "Show me container logs for the inference workload"
  • "Find which cluster has the most free GPU capacity"
  • "Rollback the last deployment"

Key features

FeatureDescription
Zero installBuilt into the PodWarden container — no separate packages to install
115 toolsFull infrastructure management: clusters, hosts, workloads, deployments, storage, secrets, config
Access levelsChoose read-only or full access — controls which tools are exposed
RBACTokens have roles (viewer, operator, admin) — the AI can only do what the token allows
Audit loggingEvery tool call through MCP is logged with token name, method, path, and status
Hub proxyConnect through Hub — no ports to open, works behind NAT
Streamable HTTPUses the MCP Streamable HTTP transport — compatible with all modern MCP clients

Getting started

Direct connection

  1. Set up a connection from your AI assistant
  2. Create a token with the appropriate role
  3. Start asking your AI assistant to manage your infrastructure

Hub proxy

  1. Enable the Hub tunnel in PodWarden Settings
  2. Create an API key in Hub Dashboard
  3. Connect your AI client to Hub's MCP endpoint
  4. Start managing your infrastructure

Supported clients

ClientTransportDirectHub Proxy
Claude Desktopstdio via mcp-remote bridgeSetupSetup
Claude CodeStreamable HTTP (native)SetupSetup
CursorStreamable HTTP (native)SetupSetup
Any MCP clientStreamable HTTPSetupSetup
MCP Integration