Skip to main content
Servers Are Up
Virtual Datacenter
PricingFree Tools
Sign inBrowse catalog
Servers Are Up
Virtual Datacenter
PricingFree Tools
Sign inBrowse catalog

Loading…

Servers Are Up

Your apps, automation and data on hardware we own. Build a private stack with predictable capacity and access through your dashboard, API or SSH.

SLA with service creditsOwned hardwareUS-based

Make room for your next idea

Explore the capacity, apps and access options that fit your workload. Check current availability and your total before you buy.

Sign up freeView Pricing

Products

  • Linux VPS
  • Windows VPS
  • Cloud & SaaS Services
  • Cloud Storage (Azure)
  • Virtual Datacenter
  • AI & Agent Hosting
  • Containers
  • Instant Apps
  • Software Platforms
  • Network builder
  • Game Servers
  • Pricing

Resources

  • Free Network Tools
  • 2026 Pricing Benchmark
  • Live SVG Badges
  • Latency & Speed Test
  • Guides & Tutorials
  • Documentation
  • API Reference
  • MCP Server
  • CLI & SDKs
  • OpenAPI & llms.txt
  • Use Cases
  • Free Migration
  • Uptime & Reliability
  • Datacenter
  • System Status
  • Network
  • Provider Comparisons Hub
  • Compare Providers

Company

  • About Us
  • Enterprise
  • Security Architecture
  • Trust Center
  • Blog
  • FAQ
  • Compliance
  • Startup Program
  • Open-Source Sponsorship
  • Press & Media Kit
  • Referral Program
  • Help Center
  • Contact Us
© Servers Are Up
TermsPrivacySLARefund PolicyDPAAcceptable Use
Service information
Docs
  • Documentation Hub
  • Choose a Product
    VMs, Containers & Cloud
  • First Linux Server
    SSH, Firewall & Apps
  • Windows Server 2025
    BYOL & Remote Desktop
  • Remote Access
  • Troubleshooting
  • FAQ
  • All Product Guides
    29 Step-by-Step Guides
  • Cloud & SaaS Catalog
    112 Cloud & SaaS Offerings
  • Azure Cloud Storage
    Hot/Cool/Archive & WORM
  • Resource Manager & RBAC
    Groups, Tags & Locks
  • Multi-Model Cloud DB
    JSONB, SQL & pgvector
  • Cloud Identity & ZTNA
    OIDC, SCIM & PIM
  • Key Vault & KMS
    Secrets & Envelope Keys
  • Cloud SIEM, SOAR & DLP
    Posture & Threat Response
  • API Gateway & Cloud DNS
    Edge WAF & DNS Zones
  • Serverless, Workflows & IoT
    Functions, Queues & DAGs
  • SaaS, Governance & Vault
    Budgets & Off-Host GRS
  • Build Web Apps with AI
  • Next.js and React
  • TypeScript and Node.js
  • npm and Tooling
  • Data and APIs
  • Deploy and Operate
  • Tutorials
  • Infrastructure
  • Automation & Regions
  • API Overview
  • API v1 Reference
    Endpoints & 23 Scopes
  • MCP Server
    129 AI Agent Tools
  • Swagger / OpenAPI 3.1
  • API Playground
  • Versioning & Sunset
  • API Token Security
    Authentication & Tokens
  • Instances API
    Compute Resources
  • Networking API
    Networks & Ports
  • Storage API Availability
    Volumes & Backups
  • Webhooks & Events
    Event Notifications
  • Rate Limits & Best Practices
    Throttling & Retries
  • sau CLI Reference
    34 Commands (v0.2)
  • Browser Web CLI
  • SDKs
  • Infrastructure as Code
    Terraform & Ansible
  • Code Examples
  • CLI & SDK Guides
  • Security Guides
  • Security at a Glance
  • Zero Trust Architecture
  • Live Trust Center
  • Compliance
Need help?

Loading documentation...

Documentation/products

Connect an AI agent to Servers Are Up over MCP

Wire Claude Code, Codex, Cursor or Gemini to /api/mcp/v1 with 129 tools, scoped tokens, resource locks and AI write guardrails.

Intermediate
15 min
Updated 2026-11-12

Deploy Ready-to-Run Infrastructure in Seconds

Linux VMs from $6/mo · Pooled Virtual Datacenters from $12/mo · Use code WELCOME20 for 20% off your first order.

Browse ServersView Pricing

Commands checked on 2026-11-12 with MCP 2025-11-25 Streamable HTTP, @serversareup/mcp-server 0.2.0.

What you will have at the end

Your AI coding agent or desktop assistant—Claude Code, OpenAI Codex, Cursor, Windsurf, Gemini CLI, or custom MCP client—will connect to Servers Are Up's Hosted Streamable HTTP MCP Server (https://serversareup.com/api/mcp/v1, exposing 129 tools) or local stdio package (@serversareup/mcp-server, 35 tools), protected by least-privilege token scopes, CanNotDelete/ReadOnly Management Locks, and server-side AI Agent Write Guardrails.

Before you start

  • An MCP-capable AI client such as Claude Code (claude), OpenAI Codex (codex), Gemini CLI (gemini), Claude Desktop, or Cursor.
  • Zero-auth discovery works immediately with no account or token (5 public tools: sau_search_catalog, sau_recommend_plan, sau_compare_providers, sau_search_docs_and_tools, sau_get_platform_facts).
  • For managing your own servers and cloud services (124 authenticated tools), mint a scoped sau_... token at Account settings > API keys (/account/api-keys).

Steps

1. Test zero-auth MCP discovery first (optional)

Verify that your network reaches the Hosted Streamable HTTP MCP endpoint (https://serversareup.com/api/mcp/v1) with a standard JSON-RPC 2.0 call—no Authorization header required for public catalog, provider comparisons, and documentation search:

curl -fsSL -X POST "https://serversareup.com/api/mcp/v1" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "sau_recommend_plan",
      "arguments": { "workload": "nextjs postgres vector rag", "budgetUsd": 45 }
    }
  }' | jq .

2. Mint a read-first or task-scoped token and set AI Write Guardrails

Before handing a token to an autonomous agent:

  1. On Account settings > API keys (/account/api-keys), start with read-only scopes (instances:read, network:read, storage:read, cloud:read, activity:read, account:read, catalog:read). Grant instances:exec, instances:write, or cloud:write only when you want the agent to run commands or provision cloud resources.
  2. Open Operations > Resource manager & settings (/dashboard/resource-manager), switch to the Portal & AI Settings tab, and choose your AI Agent Write Guardrail mode:
    • READ_ONLY: Blocks all mutating MCP/AI write operations across Resource Manager and Cloud planes even if a token carries :write scopes.
    • SAFE_MUTATIONS: Permits additive writes (creating tags, groups, or configuration keys) while blocking destructive deletes.
    • FULL_AUTONOMOUS: Allows full scoped automation (while still strictly enforcing CanNotDelete and ReadOnly locks!).

3. Register /api/mcp/v1 in Claude Code, Codex, Gemini, or Cursor

Add the hosted HTTP MCP server with a single command in your preferred agent CLI:

# Claude Code (Streamable HTTP + Bearer token)
claude mcp add --transport http serversareup https://serversareup.com/api/mcp/v1 \
  --header "Authorization: Bearer sau_your_token_here"

# OpenAI Codex CLI
codex mcp add serversareup --url https://serversareup.com/api/mcp/v1

# Google Gemini CLI
gemini mcp add --transport http serversareup https://serversareup.com/api/mcp/v1 \
  --header "Authorization: Bearer sau_your_token_here"

For Cursor (.cursor/mcp.json) or Claude Desktop, configure the serversareup server entry—or install the official Claude Code Plugin (https://serversareup.com/.claude-plugin/marketplace.json), which bundles the serversareup skill and automatic read-only tool approval hooks (packages/claude-plugin).

If your MCP host only speaks local stdio, download and run @serversareup/mcp-server (https://serversareup.com/downloads/serversareup-mcp-server.tgz) with SAU_API_TOKEN=sau_your_token_here.

4. Give your AI agent structured infrastructure tasks

Once connected, your agent has native schema-typed tools across every plane of the platform—including sau_cli_execute (which runs any structured sau CLI command over JSON), sau_rm_* (Resource Groups, Tags, Locks, RBAC, Diagnostics, Quotas, HCL/JSON export), sau_cosmos_*, sau_blob_*, sau_vault_*, sau_sentinel_*, sau_exec_instance, and sau_list_instances.

Ask your agent concrete, verifiable prompts such as:

  • "List my running servers, check my subscription quotas, and summarize any HIGH severity Cloud SIEM incidents."
  • "Create Resource Group staging-ai-rg, deploy a VECTOR_AI Cloud Database named kb-vectors, and export the group as Terraform HCL."

Check that it works

Run claude mcp list (or ask your agent "Call sau_get_platform_facts and sau_list_instances"), then verify the audit trail on Operations > Activity log (/dashboard/activity) or via the CLI:

sau monitor activity-log --limit 10 -o table

Every MCP tool call is logged with the caller token, timestamp, resource URI, and result.

What can go wrong

  • 401 Unauthorized when calling authenticated tools (sau_list_instances). Zero-auth tools work without headers, whereas account tools require Authorization: Bearer sau_.... Confirm there is no typo in the header name or token string.
  • Agent receives 403 AI_WRITE_GUARDRAIL_BLOCKED on a mutation. Your Portal & AI Settings mode is set to READ_ONLY or SAFE_MUTATIONS on /dashboard/resource-manager. Keep that guardrail enabled for exploratory sessions, or switch it temporarily when running planned provisioning.
  • Agent receives 409 RESOURCE_LOCKED. A CanNotDelete or ReadOnly lock prevented the agent from deleting or altering a protected production resource—working exactly as designed!

Good practice

  • Apply CanNotDelete locks (sau lock create ... --level CanNotDelete) to every production server, database, and storage container before giving any AI agent :write or :exec scopes.
  • Create a dedicated RBAC role assignment (AI Automation Operator) on /dashboard/resource-manager scoped only to the specific Resource Group (staging-ai-rg) the agent owns.
  • Prefer the Hosted Streamable HTTP endpoint (https://serversareup.com/api/mcp/v1) over local builds so your agent automatically receives all 129 tools and zero-downtime schema updates.

Where to go next

  • Organize resources with groups, tags, locks and RBAC
  • Create a scoped API key and send your first v1 request
  • Install the sau CLI and manage infrastructure from a terminal

Related Articles

Create a scoped API key and send your first v1 request

Read more

Route APIs with Edge WAF, rate limits and Cloud DNS

Read more

Purchase Azure-backed cloud storage with WORM locks and SAS

Read more

Frequently Asked Questions

What does the Connect an AI agent to Servers Are Up over MCP documentation guide cover?
Wire Claude Code, Codex, Cursor or Gemini to /api/mcp/v1 with 129 tools, scoped tokens, resource locks and AI write guardrails. It is rated intermediate difficulty (15 min) and applies to Servers Are Up infrastructure and workflows.
Can I manage or automate these steps through the Servers Are Up dashboard, REST API v1, or MCP server?
Yes. Every Servers Are Up server includes browser-based SSH, WebRDP, and VNC console access in the dashboard, plus programmatic control via the REST API v1 (/api/v1) and hosted Model Context Protocol server (/api/mcp/v1) using a scoped Personal Access Token.

Need hands-on help with Connect an AI agent to Servers Are Up over MCP?

Every Servers Are Up virtual machine and container includes an integrated HTML5 browser-based SSH, RDP, and VNC console in your dashboard, default-off inbound firewall rules with per-IP allow-lists, and full programmatic control via REST API v1 and Model Context Protocol (MCP). Explore our Virtual Datacenter Plans or reach out to Servers Are Up Support.

Was this article helpful?

On this page

What you will have at the endBefore you startSteps1. Test zero-auth MCP discovery first (optional)2. Mint a read-first or task-scoped token and set AI Write Guardrails3. Register /api/mcp/v1 in Claude Code, Codex, Gemini, or Cursor4. Give your AI agent structured infrastructure tasksCheck that it worksWhat can go wrongGood practiceWhere to go next