Render for AI agents
Render is a cloud platform for deploying web services, databases, and static sites, letting developers manage environments and infrastructure through one API. 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 Render.
Check a service before changing it
Get an environment's resources and active connections before making any changes.
Add an environment variable
Add a secret file or variable to an environment group so a service can pick up new configuration.
Confirm before deleting a service
Look up the service's details first, then delete it only after the team approves.
95 Render actions, graded by risk.
Every Render action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
54Look things up. Allowed by default.
- render.get_cpuGet CPU Usage
- render.get_userGet User
- render.list_logsList Logs
- render.get_memoryGet Memory Usage
- render.list_disksList Disks
- render.list_tasksList Tasks
- render.list_ownersList Owners
- render.list_routesList Routes
- render.list_deploysList Deploys
- render.get_cpu_limitGet CPU Limit
- render.list_postgresList Postgres Instances
- render.list_projectsList Projects
- render.list_servicesList Services
- render.list_webhooksList Webhooks
- render.get_disk_usageGet Disk Usage
- render.list_instancesList Instances
write
31Create and change things. Allow, or ask the user first.
- render.add_routeAdd Route
- render.add_headersAdd Header Rule
- render.update_routesUpdate Routes
- render.update_env_varUpdate Environment Variable
- render.update_headersUpdate Header Rules
- render.update_projectUpdate Project
- render.update_serviceUpdate Service
- render.create_postgresCreate Postgres Instance
- render.update_postgresUpdate Postgres Instance
- render.create_env_groupCreate Environment Group
- render.update_env_groupUpdate Environment Group
- render.create_environmentCreate Environment
- render.create_custom_domainCreate Custom Domain
- render.update_owner_log_streamUpdate Owner Log Stream
- render.update_env_group_env_varUpdate Environment Group Variable
- render.add_or_update_secret_fileAdd or Update Secret File
destructive
10Delete, cancel or archive. Ask first, or deny outright.
- render.delete_serviceDelete Service
- render.delete_key_valueDelete Key Value
- render.delete_environmentDelete Environment
- render.delete_secret_fileDelete Secret File
- render.delete_owner_log_streamDelete Owner Log Stream
- render.delete_env_group_env_varDelete Environment Group Variable
- render.delete_registry_credentialDelete Registry Credential
- render.delete_owner_metrics_streamDelete Owner Metrics Stream
- render.delete_env_group_secret_fileDelete Environment Group Secret File
- render.suspend_serviceSuspend Service
Render in three steps.
- 01Your users connect RenderThey add their Render api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Postgres Instance” can wait for the user, and “delete Service” can be denied outright.
- 03Any agent can actYour agent calls Render through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('render', { read: 'allow', write: 'ask', // create_postgres destructive: 'deny', // delete_service }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Render connects.
Users add their Render 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 Render 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 Render from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Render and Arc0, answered.
Can I use Render with Claude, ChatGPT or Cursor?
Yes. Connect Render 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 Render actions you allow.
How do users connect Render?
Users add their Render 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 Render actions can my agent take?
95 in total: 54 read, 31 write and 10 destructive, such as “create Postgres Instance”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Render?
Yes. Actions like “delete Service” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Render too?
Yes. The same Render connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Render into your agent.
Your users connect Render once, under your brand. Your agent gets 95 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan