Workstation Logo
AI Solutions
AI WorkstationsAI SME PackagesPrivate AIGPU ClustersEdge AIEnterprise AI LabAI by IndustryWSL ProxyRing Promoter
Products
AI SME PackagesCRMMarketingOpenAI AgentsWSL ProxyRing Promoter
About Us
PartnersCustomer Stories
Articles
Documentation
Blog
Contact UsLogin
Workstation

AI workstations, AI Multi Agentic Software, GPU infrastructure, and intelligent agent solutions for modern businesses.

UK: 77-79 Marlowes, Hemel Hempstead HP1 1LF

Brussels: Workstation SRL, Rue Vanderkindere 34, 1180 Uccle
BE 0751.518.683

AI Solutions

AI WorkstationsAI SME PackagesPrivate AIGPU ClustersEdge AIEnterprise AIWSL ProxyRing Promoter

Resources

ArticlesDocumentationBlogSearch

Company

About UsPartnersContact

© 2026 Workstation AI. All rights reserved.

PrivacyCookies
Home / Articles / Technology
DevOpsSecurityAIMCPCDN

Workstation WSL Proxy: API Gateway, CDN & Agent Edge

Technical brief: OpenResty hot-path gateway, CDN cache, WAF, POPs/DNS, MCP management, and the Agents Gateway / MCP Gateway roadmap

August 15, 2026Technology3 min read

Workstation WSL Proxy (also called WSLProxy) is Workstation’s complete API gateway and CDN edge control plane: live routing, WAF, cache, multi-POP DNS, and MCP for operators and AI agents. This technical brief expands the open product at wslproxy.org and the source at github.com/bwalia/wslproxy. Companion: blog · product: /wsl-proxy.

Workstation WSL Proxy cover

Agent digest.
  • What: OpenResty API gateway + CDN edge with hot-path rules (no nginx reload for day-to-day routing/WAF/cache).
  • Who: Platform, SRE, DevOps, and AI/platform teams fronting APIs, sites, and agent traffic.
  • Control: Admin UI, Swagger REST, MCP tools, wslproxy-cli (ghcr.io/bwalia/wslproxy-cli).
  • Roadmap: Agents Gateway and MCP Gateway integrations — governance for agent and MCP upstreams.

1. Positioning

Mature organisations already run reverse proxies. What they lack is an edge that is operable like a product: JSON/MCP-driven rules, multi-POP awareness, CDN-style cache, WAF with events, and a control plane agents can call. Workstation WSL Proxy is that product — open source, deployable on Docker, Ansible, or Kubernetes/k3s Helm, and branded for Workstation customer conversations as Workstation WSL Proxy.

2. Capabilities (today)

Area What you get
RoutingPath / IP / country / JWT / S3 / cookie match → proxy (305), redirect, HTML, CAPTCHA; priority + specificity
TrafficWeighted / RR / header canary / cookie sticky / least-conn; promote & rollback
WAFPolicy packs, anomaly scoring, monitor/block, events API
SSLauto-ssl / Let’s Encrypt, per-domain SSL JSON, force HTTPS
CDN / cacheEdge static cache, optional Docker blob cache, Varnish hooks
POPs + DNSEdge locations; Cloudflare A-record provisioning with guardrails
Control planeReact Admin, Next.js dashboard, Swagger, MCP, CLI
DeployDocker Compose, Ansible, Helm ingress-controller (k3s)
Observability/health /healthz /ready /metrics, traffic stats, AI log hooks

3. Architecture (hot path)

Clients and agents hit a WSLProxy POP. OpenResty runs Lua on the request path (gateway_ack → gateway_resp → balancer). Rules, WAF policies, and traffic splits load from disk or Redis and apply without an nginx reload. Reload only when server-level listen/SSL blocks change.

Clients / Agents
    → Workstation WSL Proxy POP (OpenResty + Lua)
        → match rules (JSON / Redis)
        → WAF · cache · traffic split
        → Origins / k3s / APIs / (future MCP upstreams)
Operators: Admin UI · REST · MCP · wslproxy-cli

4. MCP today vs MCP Gateway roadmap

Two related surfaces — do not confuse them:

  1. MCP management server (available): exposes WSLProxy’s own Admin capabilities as MCP tools so Claude/Cursor can configure and inspect the edge.
  2. MCP Gateway (in progress): WSLProxy as a governed front door in front of other MCP servers — auth bridging (clients never hold upstream tokens), tool/method allow-deny, audit of tools/call, and per-tool rate limits. Documented in the upstream docs/mcp-gateway.md.

5. Agents Gateway (in progress)

As organisations run multi-agent fleets, they need the same edge policies they already trust for APIs: identity bridging, rate limits, audit, canaries, and POP affinity. Agents Gateway is Workstation’s programme to route and govern agent traffic through Workstation WSL Proxy — alongside MCP Gateway — so agent solutions and API/CDN workloads share one control plane.

6. Deploy options

  • Docker Compose — local and lab stacks (docker-compose-*.yml in the repo).
  • Ansible — bare metal / VM POP builds.
  • Helm — ingress-controller style charts for k3s / Kubernetes.
  • CLI: ghcr.io/bwalia/wslproxy-cli:latest for operators and agents.

7. Why Workstation ships it

Workstation builds AI workstations, private AI, and agent platforms. Those products need a serious edge: not a one-off nginx snippet, but a gateway/CDN that ops and agents can both drive. WSLProxy is that shared edge — open at wslproxy.org, integrated into Workstation solutions as Workstation WSL Proxy.

8. Next steps

  1. Read the product page: /wsl-proxy.
  2. Explore Swagger and star the repo.
  3. Talk to Workstation about edge, CDN, Agents Gateway, and MCP Gateway deployments via contact.

Published by Workstation. Upstream docs: README, docs/mcp-gateway.md, WAF and POP guides in the GitHub repository.

Continue on the product site: https://wslproxy.com/

Share this article

More in Technology

Ring Promoter: Modern CI/CD You Cannot Miss for AI-Powered Deployments

Ring Promoter: Modern CI/CD You Cannot Miss for AI-Powered Deployments

Technical brief: ring promotion control plane, version-verified health, kubectl / GitHub Actions / k8sjob deployers, and AI-powered deployment workflows

Read more
KubePilot: CoPilot, Pilot & AutoPilot for Faster Kubernetes Incidents

KubePilot: CoPilot, Pilot & AutoPilot for Faster Kubernetes Incidents

Technical brief: three-mode incident loop, install (source/Helm/Docker/iOS), AutoPilot safety rails, MCP, runbooks, and production checklist

Read more
Muse Glimmer on Ollama: Always-On Local Agents on One GPU

Muse Glimmer on Ollama: Always-On Local Agents on One GPU

Workstation deep dive: architecture, Ollama tags/MLX, Meta benchmark matrix vs Gemma4-31B & Qwen3.6-27B, evaluation methodology, and production checklist

Read more