Agentic Broker & MCP Action Control • Included from 5 users

Secure AI agents & MCP servers
without handing raw API keys to laptops

Your developers and analysts are probably already connecting Claude Code, Cursor, or Copilot to GitHub, Jira, Slack and internal tools through MCP (Model Context Protocol, the standard way AI assistants plug into other software). This page covers how to keep the keys off laptops, ask a human before an agent changes anything, and check what comes back.

Why raw MCP configs become a security problem fast

Checking what staff paste into web chat (covered here) solves half the problem. Once teams connect AI assistants straight to business tools, three new risks show up:

  • Passwords sitting on laptops: most MCP setup guides tell developers to paste long-lived GitHub, Jira or database tokens into a plain text file on every machine.
  • All-or-nothing permissions: a token that lets an agent read tickets often lets it merge code, close tickets, message customers or delete records too. One bad prompt is all it takes.
  • Nobody checks what comes back: even when the prompt is clean, a tool can pull customer records or secrets out of an internal system and hand them to a public AI model.

What works: put a checkpoint in the middle

Instead of pointing Claude Code, Cursor or Copilot straight at a business tool with a shared admin token, point it at your own Arx AI Agent Gateway address. The console includes 1-click presets for the services teams connect most often (such as GitHub, Jira and Confluence, Linear, Notion, Stripe, and custom internal or PSA gateways), and setup on the laptop is just a few lines of config:

Example config for Claude Code, Cursor or VS Code:
{
  "mcpServers": {
    "github-prod": {
      "type": "http",
      "url": "https://app.arxcloud.io/mcp/your-tenant-id/github-prod",
      "headers": {
        "Authorization": "Bearer arx_agt_example_scoped_key"
      }
    }
  }
}
  1. Keys stay off laptops: your real GitHub or Jira token is stored encrypted inside Arx Cloud. Each developer or workflow gets their own arx_agt_... key that works for one connection and can be revoked in one click. If the real service rejects a request, the agent never sees the token or the login prompt.
  2. You decide what each tool may do: pull in the list of tools a service offers, then mark each one as allowed, needs approval, or blocked. For example, allow list_* and search_*, ask first for create_* or merge_*, and block delete_*. New tools that appear later get a safe default based on what they sound like they do. Blocked tools are hidden from the assistant so it does not waste time trying them.
  3. A human approves risky actions: when an agent tries something that needs approval, Arx Cloud pauses it and shows the request in your console. An admin clicks Approve Once, and the agent can retry that exact action one time within 30 minutes. The approval cannot be reused for a different action.
  4. Data is checked both ways: what the agent sends and what the tool returns are scanned for card numbers, personal data and API secrets. On Enterprise Hybrid and Sovereign, results are also matched against your real HIPAA, PCI & PII records. Sensitive values are masked or blocked before they reach the AI model, and every call lands in your audit log. Checks cover what your DLP rules define, so review those first.
  5. 1-click proxy pack blocks direct bypasses: enable the built-in Block Unbrokered Shadow MCP policy pack in one click so laptops cannot connect straight to public MCP endpoints around your gateway, alongside 1-click DLP packs for ChatGPT, Claude, Gemini, Copilot, and Cursor.
Start by watching, enforce when ready: each connection can run in Monitor mode, which logs what would have been blocked without interrupting anyone. There is also a one-click kill switch that cuts off every key for that connection immediately.

Scope and plan availability

To be upfront about what it covers today: the gateway works with public HTTPS MCP servers as well as private internal RFC1918 MCP servers inside an AWS VPC or on-prem datacenter (reached over an outbound-only Arx Private Access Publisher with zero inbound firewall ports). It cannot see MCP tools that run purely locally on a developer's own laptop (local stdio servers) unless you move them behind a central HTTP MCP service.

  • Arx Business Team ($10/user/mo on 2-Year, 5+ seats, 30-day free trial): includes the AI Agent Gateway (up to 10 connections and 25 keys per connection), Arx Private Access Publishers for internal MCP servers, per-tool rules, human approvals, data scanning in both directions, and searchable console audit logs.
  • Arx Enterprise Hybrid ($20/user/mo on 2-Year, 25+ seats, 30-day free trial): adds Exact Data Match (HIPAA, PCI & PII) on everything agents send and receive, real-time SIEM streaming, SAML single sign-on with contractor session watermarking, and dedicated VPC relays.
  • Arx Enterprise Sovereign ($30/user/mo on 2-Year, 75+ seats, 30-day free trial): adds Dedicated / Sovereign VPC isolation, unlimited vaulted MCP connectors, custom HIPAA BAA / DPA redlines, security questionnaires, and a Dedicated Solutions Engineer.

Want a 15-minute MCP & AI Agent walkthrough?

Tell us which AI tools your team connects to, and we will send the Shadow AI checklist plus a link to book a walkthrough.

  • Real keys stay in the vault, not on laptops
  • Allow, ask first, or block, tool by tool
  • Starts at 5 seats with a 30-day free trial

One email with the checklist and demo link. No newsletter, no spam. Privacy

Frequently asked questions

Does the AI agent ever see our GitHub, Jira, or SaaS API token?
No. Your real tokens are stored encrypted in Arx Cloud and only added to a request after it passes your rules and data checks. Each developer or agent gets its own arx_agt_ key that you can revoke at any time.
Which MCP servers and AI clients work with Arx Cloud?
Any assistant that connects to a remote MCP server over HTTPS, including Claude Code, Claude Desktop, Cursor, and VS Code Copilot. You can connect public SaaS MCP servers in one click or attach an inside-out Arx Private Access Publisher to broker private RFC1918 MCP servers inside your VPC or office LAN with zero open firewall ports.
Which Arx Cloud plans include AI Agent Gateway?
The AI Agent Gateway is included in Arx Business Team from $10/seat/month (5+ seats), Arx Enterprise Hybrid at $20/seat/month (25+ seats), and Arx Enterprise Sovereign at $30/seat/month (75+ seats), with Hybrid and Sovereign adding Exact Data Match on what agents send and receive. It is not part of the personal plans.