Carvector MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from npm. Last commit 11 Jun 2026.
Vehicle specs, federal recalls, and OBD-II DTC reference for AI agents via MCP.
Today is the operative word: we check Carvector 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 carvector-mcp -- npx -y carvector-mcp
{
"mcpServers": {
"carvector-mcp": {
"args": [
"-y",
"carvector-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.carvector-mcp]
command = "npx"
args = ["-y", "carvector-mcp"]
{
"mcpServers": {
"carvector-mcp": {
"args": [
"-y",
"carvector-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"carvector-mcp": {
"args": [
"-y",
"carvector-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
CARVECTOR_API_KEY (Your CarVector API key (free at carvector.io)).
The author declared them in the registry entry; get the values from the project itself.
Self-hosted long-term memory for AI agents over MCP — hierarchical recall backed by pgvector
Federated local-first search across transcripts, files, KG, vectors and the web for AI agents.
Graph + vector memory for agents: recall, ingest, search, distill. Local or remote backend.
Persistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.
Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.
Local-first memory for AI agents: SQLite FTS5, deterministic recall, no vector DB, no cloud.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Answers built from our own checks of this server.