Developer · Local MCP server
Runeward
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Runewardd/runeward- Version
- 0.1.4
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- OCI image (Docker)
- Published
- 2026-07-08
- Updated
- 2026-07-08
- Publisher
- Runewardd (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/Runewardd) · how
- Listed under
- Docker MCP servers, Kubernetes MCP servers
- Repository
- github.com/Runewardd/runeward
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| OCI image (Docker) | ghcr.io/runewardd/runeward:v0.1.4 | - | stdio |
How to connect Runeward
Runeward runs locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/runewardd/runeward:v0.1.4. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run - the usual command is docker run -i --rm -e RUNEWARD_CONFIG_DIR -e RUNEWARD_STATE_DIR ghcr.io/runewardd/runeward:v0.1.4. It reads these environment variables: RUNEWARD_CONFIG_DIR and RUNEWARD_STATE_DIR; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"runeward": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"RUNEWARD_CONFIG_DIR",
"-e",
"RUNEWARD_STATE_DIR",
"ghcr.io/runewardd/runeward:v0.1.4"
],
"env": {
"RUNEWARD_CONFIG_DIR": "<value>",
"RUNEWARD_STATE_DIR": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Run PythonRun Python code from natural language prompts, with optional PyPI package install. | Remote · HTTPLive check: ✗ no handshake |
| RunCabinPut websites online from chat - instant free HTTPS, real domains, zero DNS or API-key setup. | Remote · HTTPLive check: sign-in required |
| Runcomfy MCPRemote MCP for RunComfy: ComfyUI deployments, hosted models, LoRA training. 31 tools. | Remote · HTTPLive check: sign-in required |
| RuneEvidence-backed codebase understanding with file:line citations, for AI clients over MCP. | Local · stdio |
| RunlogVerified registry of third-party-system knowledge - the external-dependency layer for agent memory. | Remote · HTTPLive check: ✗ no handshake |
| RunpodLaunch, scale, and manage GPU pods and serverless endpoints across regions. | Local · stdio |
| Runtime CloudLinux microVM sandboxes for AI agents: run commands, files, processes, pause and wake. | Remote & Local · HTTP, stdioLive check: sign-in required |
| Runtime Eol Deploy Block AuditFinds the end-of-life runtimes an AI assistant still writes for you - node:20, python3.9, ubuntu-22. | Local · stdio |