Netlify for AI agents
Netlify is a platform for deploying and hosting web projects, used here to inspect and manage sites, builds, and deploy configuration. 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 Netlify.
Check a deploy's status
Look up a recent deploy's status and logs to confirm a build succeeded, read-only.
Check project environment settings
Read a project's environment configuration before troubleshooting a build issue, a read-only check with no changes.
Approve before updating deploy settings
Require approval before updating a project's deploy configuration, since it affects the live site.
9 Netlify actions, graded by risk.
Every Netlify action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- netlify.get_netlify_coding_contextGet-netlify-coding-context
write
8Create and change things. Allow, or ask the user first.
- netlify.netlify_team_services_readerNetlify-team-services-reader
- netlify.netlify_user_services_readerNetlify-user-services-reader
- netlify.netlify_deploy_services_readerNetlify-deploy-services-reader
- netlify.netlify_deploy_services_updaterNetlify-deploy-services-updater
- netlify.netlify_project_services_readerNetlify-project-services-reader
- netlify.netlify_project_services_updaterNetlify-project-services-updater
- netlify.netlify_extension_services_readerNetlify-extension-services-reader
- netlify.netlify_extension_services_updaterNetlify-extension-services-updater
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Netlify in three steps.
- 01Your users connect NetlifyThey sign in to Netlify on Arc0 Connect, under your brand, and approve the access you ask for.
- 02You set the rulesReads run, and writes like “netlify-team-services-reader” can wait for the user to approve.
- 03Any agent can actYour agent calls Netlify through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('netlify', { read: 'allow', write: 'ask', // netlify_team_services_reader destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Netlify connects.
Netlify runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Netlify through the same endpoint, policies and audit log as every other app.
The same Netlify 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
- OAuth 2.0 (MCP)
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Netlify from any agent.
Netlify and Arc0, answered.
Can I use Netlify with Claude, ChatGPT or Cursor?
Yes. Connect Netlify 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 Netlify actions you allow.
How do users connect Netlify?
Netlify runs its own MCP server behind OAuth. Arc0 registers the client, users approve access on Arc0 Connect, and your agent reaches Netlify through the same endpoint, policies and audit log as every other app.
Which Netlify actions can my agent take?
9 in total: 1 read, 8 write and 0 destructive, such as “netlify-team-services-reader”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Netlify?
Yes. Allow read actions and deny writes in the Netlify policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Netlify too?
Yes. The same Netlify connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Netlify into your agent.
Your users connect Netlify 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