Weaviate MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 23 Sep 2026.
MCP server for Weaviate: collections, objects, GraphQL search. Works with any instance.
Today is the operative word: we check Weaviate 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 weaviate-mcp -- npx -y weaviate-mcp
{
"mcpServers": {
"weaviate-mcp": {
"args": [
"-y",
"weaviate-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.weaviate-mcp]
command = "npx"
args = ["-y", "weaviate-mcp"]
{
"mcpServers": {
"weaviate-mcp": {
"args": [
"-y",
"weaviate-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"weaviate-mcp": {
"args": [
"-y",
"weaviate-mcp"
],
"command": "npx"
}
}
}
MCP server for Milvus: collections, stats, search. Works with any instance.
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
MCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.
MCP server for the xAI Grok API — chat, vision, search, and embeddings
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.
Answers built from our own checks of this server.