Koma Core MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 30 installs a week from npm. Last commit 13 Oct 2026.
Protected RAG storage — agents discover public metadata, content only by access token.
What the code does
We read the source, 5 d ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
const result = spawnSync(process.execPath, [live], { stdio: 'inherit' });
const settingsPath = path.join(projectRoot, details.settingsRelativePath);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Nothing serious here today
Today is the operative word: we check Koma Core MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 koma-core-mcp -- npx -y koma-core-mcp{
"mcpServers": {
"koma-core-mcp": {
"command": "npx",
"args": [
"-y",
"koma-core-mcp"
]
}
}
}[mcp_servers.koma-core-mcp]
command = "npx"
args = ["-y", "koma-core-mcp"]{
"mcpServers": {
"koma-core-mcp": {
"command": "npx",
"args": [
"-y",
"koma-core-mcp"
]
}
}
}{
"servers": {
"koma-core-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"koma-core-mcp"
]
}
}
}Optional settings from the registry entry, left out of the block above:
KOMA_MASTER_KEY (HKDF master key for content tokens (demo key fallback if unset)).
Alternatives to Koma Core MCP
same job, measured the same wayLocal, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.
x402 clean article text and metadata for AI/RAG. $0.002 per successful article.
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
x402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Governed graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
Role-based access to your Qdrant vector store, via MCP. OIDC in, scoped JWTs out.
Koma Core MCP — questions
Answers built from our own checks of this server.