AI Wiki · Mediocre Security
ProductAI security tooling

Citrix SecurSpaces

Expanded Nov 5 2026 to run agents in isolated workspaces with restricted file access, protected credentials and a central control plane, built on SecurAccess ZTNA and NetScaler AI Gateway.

Expanded Nov 5 2026 to run agents in isolated workspaces with restricted file access, protected credentials and a central control plane, built on SecurAccess ZTNA and NetScaler AI Gateway; adds a free Community Edition (Citrix blog, vendor claim).

How it works

Each SecurSpaces Flex workspace is an isolated, sandboxed Linux container, and AI agents (such as Claude Code) run in them under the same control plane and policy as human developers. Model traffic goes through an AI gateway (NetScaler AI Gateway or Envoy AI Gateway), which tags each request with user, project and workspace for token-cost tracking. SecurSpaces doesn’t police MCP tool calls itself; Citrix points to NetScaler as an MCP Gateway (announced July 2026) or SecurAccess ZTNA for that. Compare open-source agent sandboxes like Strands Box and Perplexity SPACE.

Connections

Citrix SecurSpaces and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Product Strands Box

Sources

  1. Citrix, “SecurSpaces as a platform for agentic workloads”
  2. Citrix, “Configure AI Gateway routing in SecurSpaces”
  3. Help Net Security, “Citrix launches MCP Gateway to secure enterprise AI agents”