Skilder Logo
Concepts

Runtimes

How Skilder runtimes execute MCP servers and route tool calls between agents and tools across different deployment modes.

A runtime manages MCP server processes and routes tool calls between agents and the tools those servers provide.

Runtime Modes

The Skilder runtime operates in one of four modes, depending on how it's configured:

ModeActivationUse Case
MCP_STDIOUSER_KEY env var setConnect a single agent (e.g., Claude Desktop) to Skilder via stdio
EDGERUNTIME_KEY or SYSTEM_KEY set, no REMOTE_PORTExecute MCP tools on edge hardware, connected via NATS
EDGE_MCP_STREAMRUNTIME_KEY/SYSTEM_KEY + REMOTE_PORT setEdge runtime exposed via HTTP (SSE + Streamable HTTP transports)
STANDALONE_MCP_STREAMOnly REMOTE_PORT setPure MCP server over HTTP, no NATS connection needed

MCP_STDIO (User Agent Mode)

The simplest mode. One runtime, one agent, connected via stdin/stdout. This is what Claude Desktop and similar local clients use.

USER_KEY=USK_your_key npx @skilder-ai/runtime

EDGE (Runtime Tool Executor)

A long-running process that connects to the Skilder backend via NATS and executes MCP tools. Used for managed cloud deployments or on-premises infrastructure.

RUNTIME_KEY=RTK_your_key NATS_SERVERS=nats://... npx @skilder-ai/runtime

EDGE_MCP_STREAM (Edge with Remote Access)

Same as EDGE, but also exposes SSE and Streamable HTTP endpoints for remote MCP clients (Copilot, ChatGPT, Cursor).

RUNTIME_KEY=RTK_your_key REMOTE_PORT=3001 NATS_SERVERS=nats://... npx @skilder-ai/runtime

STANDALONE_MCP_STREAM (Headless MCP Server)

Runs as a pure HTTP MCP server without NATS. Useful for standalone deployments where you want MCP access without the full Skilder backend.

REMOTE_PORT=3001 npx @skilder-ai/runtime

What the Runtime Does

  • Process lifecycle — Starts, monitors, and stops MCP server processes as needed. Supports lazy-start with idle timeout.
  • Environment variables and secrets — Injects configuration and credentials into each server at startup.
  • Tool call routing — Receives requests from NATS (or HTTP), forwards to the correct MCP server, returns results.
  • Isolation — Each MCP server runs in its own process.
  • OAuth token provisioning — Transparently provides OAuth tokens to MCP servers that need them.
  • Asset caching — Resolves @skilder-asset:/ paths to local cached files for cross-tool asset sharing.

MCP Server Status

StatusMeaning
ConnectedHealthy, tools available
StartingInitializing, wait and refresh
PendingBeing set up
IdleStopped due to inactivity, will restart on next tool call
ErrorSomething failed — check error details
DisconnectedStopped, try restart

Supported Transports

TransportDescription
STDIOLocal stdin/stdout — used by Claude Desktop, local agents
SSEServer-Sent Events over HTTP — used by some remote clients
Streamable HTTPModern HTTP-based MCP transport — used by ChatGPT, Copilot

Benefits

  • Zero setup — MCP servers run as soon as you install them. No manual process management.
  • Managed uptime — The runtime handles process health, restarts, and resource allocation.
  • Consistent environment — Standardized runtime eliminates configuration drift.

Environment Variables

MCP servers need credentials or config to connect to external services. Configure these as environment variables when installing or editing a server. The runtime injects them at startup. Sensitive values are stored securely and never exposed after initial entry.

See Configuration for the full list of runtime environment variables.