Vectros MCP
An official MCP server that exposes Vectros' data plane to agents, enabling search, records, documents, folders, and grounded inference as native tools with tenant isolation and scoped-key enforcement.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Perform hybrid search over records and documents
- Read and write typed records
- Ingest and manage documents
- Execute grounded RAG inference
Source and maintenance
Community listingRegistry 0.18.2
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
@vectros-ai/mcp-server 0.18.2
npm
@vectros-ai/mcp-server package definition
{
"version": "0.18.2",
"transport": "stdio",
"identifier": "@vectros-ai/mcp-server",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"environmentVariables": [
{
"name": "VECTROS_API_KEY",
"isRequired": true,
"description": "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."
},
{
"name": "VECTROS_KEYRING_ALIAS",
"description": "Optional. When VECTROS_API_KEY is unset and the vectros CLI is installed, resolve this keyring entry instead of the active one."
},
{
"name": "VECTROS_API_BASE_URL",
"description": "Override the API base URL (default https://api.vectros.ai). Must be an official *.vectros.ai host."
},
{
"name": "VECTROS_MCP_TOOLS",
"description": "Comma-separated subset of tool names to register (default: all 23 tools)."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
Cursor configuration
{
"mcpServers": {
"vectros-mcp": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server@0.18.2"
],
"env": {
"VECTROS_API_KEY": "<YOUR_VECTROS_API_KEY>",
"VECTROS_KEYRING_ALIAS": "<YOUR_VECTROS_KEYRING_ALIAS>",
"VECTROS_API_BASE_URL": "<YOUR_VECTROS_API_BASE_URL>",
"VECTROS_MCP_TOOLS": "<YOUR_VECTROS_MCP_TOOLS>"
}
}
}
}Cline
Cline configuration
{
"mcpServers": {
"vectros-mcp": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server@0.18.2"
],
"env": {
"VECTROS_API_KEY": "<YOUR_VECTROS_API_KEY>",
"VECTROS_KEYRING_ALIAS": "<YOUR_VECTROS_KEYRING_ALIAS>",
"VECTROS_API_BASE_URL": "<YOUR_VECTROS_API_BASE_URL>",
"VECTROS_MCP_TOOLS": "<YOUR_VECTROS_MCP_TOOLS>"
}
}
}
}VS Code
VS Code configuration
{
"servers": {
"vectros-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server@0.18.2"
],
"env": {
"VECTROS_API_KEY": "<YOUR_VECTROS_API_KEY>",
"VECTROS_KEYRING_ALIAS": "<YOUR_VECTROS_KEYRING_ALIAS>",
"VECTROS_API_BASE_URL": "<YOUR_VECTROS_API_BASE_URL>",
"VECTROS_MCP_TOOLS": "<YOUR_VECTROS_MCP_TOOLS>"
}
}
}
}Claude Desktop
Claude Desktop configuration
{
"mcpServers": {
"vectros-mcp": {
"command": "npx",
"args": [
"-y",
"@vectros-ai/mcp-server@0.18.2"
],
"env": {
"VECTROS_API_KEY": "<YOUR_VECTROS_API_KEY>",
"VECTROS_KEYRING_ALIAS": "<YOUR_VECTROS_KEYRING_ALIAS>",
"VECTROS_API_BASE_URL": "<YOUR_VECTROS_API_BASE_URL>",
"VECTROS_MCP_TOOLS": "<YOUR_VECTROS_MCP_TOOLS>"
}
}
}
}Let your agent find its tools
Find servers like Vectros MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.