Blog

Google has two distinct retrieval products under the Vertex AI brand. Vector Search (formerly Matching Engine) is a managed ANN index. Vertex AI Search is a full Discovery Engine service with keyword, hybrid, and listing capabilities. Gateco supports both — here is when to use each.

The Gateco MCP server gives Claude Desktop, Cursor, and any MCP-compatible host policy-enforced access to your vector knowledge bases. Six tools, markdown-only output, denied content never surfaces. Available on all plans for retrieval tools; Grounded Answers requires Growth+.

Gateco now supports 1-hop relationship-based access control: policies can check whether a principal has a named relationship to a resource. Owner, assignee, project member — any relationship you define. Here is how it works and when to use it over RBAC and ABAC.

A summary of everything that shipped this month: relationship-based access control, API key authentication, SDK v1.0, and our new Trust Center.

Gateco now integrates with Google Vertex AI Vector Search — bringing deny-by-default retrieval, ABAC policies, and audit trails to GCP-hosted vector workloads. Vertex AI Search is also now available.

Azure AI Search gives you world-class hybrid retrieval. Gateco decides who's allowed to see the results. Here's why enterprise RAG needs both — and how they compose.

A step-by-step guide to connecting your identity provider to Gateco for policy-enforced AI retrievals.

Gateco now supports four distinct retrieval modes. Here's when to reach for each one — and why hybrid might be your new default.

Today we're launching Gateco — the security middleware between AI agents and organizational knowledge. Deny-by-default retrieval, 12 vector DB connectors, and full audit trails. Here's why we built it.