Saucelabs for AI agents
Sauce Labs runs automated browser and mobile app tests in the cloud, giving QA and engineering teams a testing grid across real devices and browsers. 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 Saucelabs.
List running test jobs
Reads current test jobs on the account to check which builds are still executing.
Check supported platforms before a run
Looks up which browser and device combinations are available before scheduling a test suite.
Confirm tunnel version before deploying
Reads the current Sauce Connect tunnel version so a test run isn't started on an outdated proxy.
6 Saucelabs actions, graded by risk.
Every Saucelabs action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- saucelabs.list_jobsList Jobs
- saucelabs.get_platformsGet Supported Platforms
- saucelabs.get_api_statusGet API Status
- saucelabs.get_appium_eolGet Appium EOL
- saucelabs.get_api_definitionGet Performance API Definition
- saucelabs.get_tunnel_versionsGet Tunnel Versions
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.
Saucelabs in three steps.
- 01Your users connect SaucelabsThey add their Saucelabs username and password 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 Saucelabs through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('saucelabs', { 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 Saucelabs connects.
Users add their Saucelabs username and password 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 Saucelabs 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
- Username and password
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Saucelabs from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Saucelabs and Arc0, answered.
Can I use Saucelabs with Claude, ChatGPT or Cursor?
Yes. Connect Saucelabs 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 Saucelabs actions you allow.
How do users connect Saucelabs?
Users add their Saucelabs username and password 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 Saucelabs actions can my agent take?
6 in total: 6 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Saucelabs?
Yes. Allow read actions and deny writes in the Saucelabs policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Saucelabs too?
Yes. The same Saucelabs connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Saucelabs into your agent.
Your users connect Saucelabs once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan