Studium runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 12 Nov 2026.
Studium lessons over MCP: play, review over days, build a lesson from your sources.
We read the source, 17 min ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const runGit: GitExec = (command, args, options) => execFileSync(command, [...args], {
dom.window.eval(source);
with open(os.path.join(udir, f"{universe['id']}.yaml"), "w", encoding="utf-8") as f:
proc = subprocess.run(cmd, cwd=str(directory), env=env, capture_output=True,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add studium -- npx -y studium-mcp
{
"mcpServers": {
"studium": {
"command": "npx",
"args": [
"-y",
"studium-mcp"
]
}
}
}
[mcp_servers.studium]
command = "npx"
args = ["-y", "studium-mcp"]
{
"mcpServers": {
"studium": {
"command": "npx",
"args": [
"-y",
"studium-mcp"
]
}
}
}
{
"servers": {
"studium": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"studium-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
STUDIUM_HOME (Where lessons and progress live (default ~/.studium)), BUNDLES_ROOT (A folder of lessons looked up first, for example a teacher's course), STUDIUM_EPHEMERAL (Set to 1 to keep everything in memory and write nothing), LITELLM_BASE_URL (A judge model endpoint for written answers; empty calls no model).
Go over your Shogi Dojo games, explore the moves played from a position, and make review quizzes.
Turn quiz questions from your chat into a ready-to-play pub quiz on quizquiz.co.
Build, review and share AI-structured data rooms from your Pageform workspace.
MCP server for Fabrx - Build APIs from documents in your IDE
Open-source vibe coding hosting over MCP: your agent builds, previews and publishes web apps.
Build browser games on gamedev.pl from your coding agent.
Link building outreach from your agent: review drafts, send the batch, answer publisher replies.
A project planning board your AI reads and updates over MCP, so the plan stays one plan.
Answers built from our own checks of this server.