UniFi for AI agents
UniFi Site Manager monitors network health and inventory across a UniFi account's sites, used by IT teams keeping an eye on connectivity without touching device configuration directly. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in UniFi.
List sites and devices
Pull the current inventory of sites and devices as a read-only check.
Check ISP health metrics
Read internet connection health for a site to spot a developing outage.
Review an SD-WAN configuration
Read a site's SD-WAN config and status before flagging it for a network engineer.
9 UniFi actions, graded by risk.
Every UniFi action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
9Look things up. Allowed by default.
- unifi.get_hostGet Host
- unifi.list_hostsList Hosts
- unifi.list_sitesList Sites
- unifi.list_devicesList Devices
- unifi.get_isp_metricsGet ISP Metrics
- unifi.get_sd_wan_configGet SD-WAN Config
- unifi.query_isp_metricsQuery ISP Metrics
- unifi.list_sd_wan_configsList SD-WAN Configs
- unifi.get_sd_wan_config_statusGet SD-WAN Config Status
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
UniFi in three steps.
- 01Your users connect UniFiThey add their UniFi api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls UniFi through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('unifi', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How UniFi connects.
Users add their UniFi api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same UniFi connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use UniFi from any agent.
UniFi and Arc0, answered.
Can I use UniFi with Claude, ChatGPT or Cursor?
Yes. Connect UniFi to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the UniFi actions you allow.
How do users connect UniFi?
Users add their UniFi api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which UniFi actions can my agent take?
9 in total: 9 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in UniFi?
Yes. Allow read actions and deny writes in the UniFi policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call UniFi too?
Yes. The same UniFi connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug UniFi into your agent.
Your users connect UniFi once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan