Get started

Openlayer for AI agents

Openlayer is an AI quality platform for monitoring production model data, running evaluations, and tracking test results across projects. ML teams use it to catch regressions before they reach users. 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.

Connect OpenlayerSee the 10 actions ↓
AI and modelsAPI keyMCP + RESTopenlayer.com
AUDIT LOG · OPENLAYERPOLICY: acme-support
09:41:07 · claude · u_8f2read
openlayer.list_tests
List Tests✓ allowed · 212ms
09:41:08 · claude · u_8f2read
openlayer.get_workspace
Get Workspace✓ allowed · 164ms
EVERY OPENLAYER CALL, ON THE RECORD
01 · USE CASES

What agents do in Openlayer.

01

Check test results for a project

List recent test results read-only to see whether a model version is passing quality checks.

02

Review production data sources

List data sources feeding a monitored project to confirm the right data is being tracked.

03

Compare project versions

Pull test results across two project versions to see whether a change improved quality.

02 · ACTIONS

10 Openlayer actions, graded by risk.

Every Openlayer action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

10

Look things up. Allowed by default.

  • openlayer.list_tests
    List Tests
  • openlayer.get_workspace
    Get Workspace
  • openlayer.list_projects
    List Projects
  • openlayer.get_data_source
    Get Data Source
  • openlayer.list_data_sources
    List Data Sources
  • openlayer.list_test_results
    List Test Results
  • openlayer.get_project_version
    Get Project Version
  • openlayer.list_project_versions
    List Project Versions
  • openlayer.list_data_source_test_results
    List Data Source Test Results
  • openlayer.list_project_version_test_results
    List Project Version Test Results

write

0

Create and change things. Allow, or ask the user first.

  • No write actions.

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Openlayer in three steps.

  1. 01Your users connect OpenlayerThey add their Openlayer api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Openlayer through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('openlayer', {
  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
04 · AUTH AND DATA

How Openlayer connects.

Users add their Openlayer 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 Openlayer 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
05 · WORKS WITH

Use Openlayer from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Openlayer and Arc0, answered.

Q01

Can I use Openlayer with Claude, ChatGPT or Cursor?

Yes. Connect Openlayer 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 Openlayer actions you allow.

Q02

How do users connect Openlayer?

Users add their Openlayer 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.

Q03

Which Openlayer actions can my agent take?

10 in total: 10 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Openlayer?

Yes. Allow read actions and deny writes in the Openlayer policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Openlayer too?

Yes. The same Openlayer connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Openlayer into your agent.

Your users connect Openlayer once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect OpenlayerBrowse all apps →

Free to build · MCP + REST · Audit log on every plan