Vectros AI MCP Server
by vectros-aiio.github.vectros-ai/mcp-serverv0.18.0
Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.
context tax
queued
security
queued
cold start
queued
freshness
Active7d ago
Install Vectros AI MCP server
Install in Claude Code
claude mcp add vectros-ai -e VECTROS_API_KEY='<vectros-api-key>' -- npx -y @vectros-ai/mcp-serverInstall in Cursor
{
"mcpServers": {
"vectros-ai": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server"
],
"env": {
"VECTROS_API_KEY": "<vectros-api-key>"
}
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"vectros-ai": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server"
],
"env": {
"VECTROS_API_KEY": "<vectros-api-key>"
}
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"vectros-ai": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server"
],
"env": {
"VECTROS_API_KEY": "<vectros-api-key>"
}
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"vectros-ai": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server"
],
"env": {
"VECTROS_API_KEY": "<vectros-api-key>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Configuration
| Variable | Required | Secret | Description |
|---|---|---|---|
| VECTROS_API_KEY | yes | yes | Vectros API key. Use a least-privilege scoped key (ssk_...); mint one with `npx -y @vectros-ai/cli bootstrap`. Required for a registry install, which cannot assume any other tooling is present. If you also install the vectros CLI (0.9.0+), the server can instead resolve the key from its keyring and this can be left unset. |
| VECTROS_KEYRING_ALIAS | — | — | Optional. When VECTROS_API_KEY is unset and the vectros CLI is installed, resolve this keyring entry instead of the active one. |
| VECTROS_API_BASE_URL | — | — | Override the API base URL (default https://api.vectros.ai). Must be an official *.vectros.ai host. |
| VECTROS_MCP_TOOLS | — | — | Comma-separated subset of tool names to register (default: all 23 tools). |
Freshness
Active — last maintenance signal 7d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-10-02 · 7d ago · GitHub
Latest release
2026-10-02 · 7d ago · GitHub · v0.18.0
Package published
no data · npm/PyPI
Registry entry updated
2026-10-02 · 7d ago · official registry · v0.18.0
FAQ
›How do I install the Vectros AI MCP server in Claude Code?
Run: claude mcp add vectros-ai -e VECTROS_API_KEY='<vectros-api-key>' -- npx -y @vectros-ai/mcp-server. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Vectros AI require an API key?
Yes. It expects VECTROS_API_KEY, of which 1 is a secret.
›Can I use Vectros AI as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Vectros AI in the official MCP registry?
Yes, as io.github.vectros-ai/mcp-server.
Alternatives to Vectros AI
Other memory MCP servers.