Smart Connections MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 63 installs a week from npm. Last commit 22 Aug 2026.
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
Today is the operative word: we check Smart Connections MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 smart-connections-mcp -- npx -y smart-connections-mcp
{
"mcpServers": {
"smart-connections-mcp": {
"args": [
"-y",
"smart-connections-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.smart-connections-mcp]
command = "npx"
args = ["-y", "smart-connections-mcp"]
{
"mcpServers": {
"smart-connections-mcp": {
"args": [
"-y",
"smart-connections-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"smart-connections-mcp": {
"args": [
"-y",
"smart-connections-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SMART_VAULT_PATH (One or more absolute Obsidian vault paths, comma-separated (alias: SMART_VAULT_PATHS)).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Minimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.
Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.
Local semantic search — embedding-powered grep for files, zero external services.
BM25 search + tree navigation over markdown docs for AI agents. No embeddings, no LLM calls.
Bilingual dual memory with SSC for AI agents. Semantic search, embeddings, profiles.
Search self-contained .pikelet knowledge artifacts over MCP — no vector DB, no embedding API.
Answers built from our own checks of this server.