Kubernetes Ephemeral Job MCP server

mcp-k8s-ephemeral-job

English | Русский

Public OSS MCP server (Go, MIT) that spawns an ephemeral Kubernetes Job/pod from a caller-chosen image, runs a command inside it, returns exitcode / stdout / artifacts, and deletes the pod. The server builds the pod manifest in code** — the caller passes parameters only, never raw YAML.

It is the "operating room" counterpart to mcp-exec (the "scalpel"): where mcp-exec runs a single Python file in a locked-down, network-less sandbox in milliseconds, this one spins up a full pod with the toolchain/image you choose, controlled network (clone repos, pull deps), long tasks and file artifacts out. They complement each other.

Works over three transports — stdio / HTTP / SSE — with an identical tool set everywhere (official modelcontextprotocol/go-sdk).

Tools

run_job — run and wait

Input: { image (required), command (required), files?, env?, limits?, timeouts?, workdir?, clone? } Output: { exitcode, stdout, stderr, duration_ms, status, artifacts, truncated }

timeout is a normal result, not a tool error. Only invalid input (empty image/command, image not in the allowlist, bad file path) is a tool-call error.

• status is one of succeeded / failed / timeout / error. A non-zero exit_code or a

pod logs. stderr is reserved and always empty, so adding stream separation later stays backward-compatible.

• stdout carries the container's combined stdout+stderr — Kubernetes merges the two streams in

Exceeding a cap never loses data silently: the matching truncated flag is set.

• Artifacts (files from the working directory) come back inline (base64) under a size cap.

• The manifest is built deterministically by the server — no raw YAML from the caller.

submitjob / fetchjob — run in the background

Shortened. The full README is on GitHub.