Fusionpact Vectordb runs on your own machine — the client starts it, so there is no endpoint to ping. 55 installs a week from npm. Last commit 10 Mar 2026.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.
Today is the operative word: we check Fusionpact Vectordb 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 fusionpact-vectordb -- npx -y fusionpact
{
"mcpServers": {
"fusionpact-vectordb": {
"command": "npx",
"args": [
"-y",
"fusionpact"
]
}
}
}
[mcp_servers.fusionpact-vectordb]
command = "npx"
args = ["-y", "fusionpact"]
{
"mcpServers": {
"fusionpact-vectordb": {
"command": "npx",
"args": [
"-y",
"fusionpact"
]
}
}
}
{
"servers": {
"fusionpact-vectordb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"fusionpact"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
EMBEDDING_PROVIDER (Embedding provider: ollama (free), openai, or mock).
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval
MCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
Self-hosted memory for AI agents over MCP: knowledge graph, vectors, graph RAG, cited answers.
Local FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.
Answers built from our own checks of this server.