ragnarok runs on your own machine — the client starts it, so there is no endpoint to ping. 331 installs a week from pypi. Last commit 6 Nov 2026.
Local RAG search over Obsidian vaults: SQLite hybrid search with local Ollama embeddings.
What the code does
We read the source, 20 h 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.
out = subprocess.run(cmd, cwd=cwd, env={**os.environ, **env}, capture_output=True, text=True, timeout=900)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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 ragnarok -- uvx ragnarok-mcp{
"mcpServers": {
"ragnarok": {
"command": "uvx",
"args": [
"ragnarok-mcp"
]
}
}
}[mcp_servers.ragnarok]
command = "uvx"
args = ["ragnarok-mcp"]{
"mcpServers": {
"ragnarok": {
"command": "uvx",
"args": [
"ragnarok-mcp"
]
}
}
}{
"servers": {
"ragnarok": {
"type": "stdio",
"command": "uvx",
"args": [
"ragnarok-mcp"
]
}
}
}Optional settings from the registry entry, left out of the block above:
RAGNAROK_HOME (The folder that holds config.toml, data/ and logs/. Default: ~/.ragnarok).
Alternatives to ragnarok
same job, measured the same wayLocal hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Local code search for AI coding agents: hybrid keyword + semantic + SQL over an index in your repo.
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Token-light local memory with SQLite hybrid retrieval for MCP agents.
ragnarok — questions
Answers built from our own checks of this server.