Intern

Send a site, not a deck.

CommunityDegradedNo sign-inGlobalFreeCan modify data

What it can do

  • Intern Get Authoring Guide: Return the supported browser SDK import and examples for active site plugins.
  • Intern Auth Status: Return the current Intern user and organization without exposing credentials.
  • Intern List Sites: List sites in the authorized Intern organization.

What data it sees

Do you need an account

No: the server works without sign-in

Send a site, not a deck. Turn an idea into a dashboard, launch room, report, or team site. Connect your agent to Intern, sign in, and tell it what to build. Sites are private by default. Share them when you are ready.

How to connect

How to connect Intern to Claude

The server address to paste into Claude settings:

https://intern--archastro.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Intern to ChatGPT

The server address to paste into ChatGPT settings:

https://intern--archastro.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Intern to Cursor

The server address to paste into Cursor settings:

https://intern--archastro.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (19)

Raw names from tools/list. Only developers need these.

intern_get_authoring_guideReturn the supported browser SDK import and examples for active site plugins.
intern_auth_statusReturn the current Intern user and organization without exposing credentials.
intern_list_sitesList sites in the authorized Intern organization.
intern_list_available_pluginsList the public plugin catalog. New catalog plugins appear here without a hosted MCP update.
intern_create_siteCreate a remotely editable site and optionally request catalog plugins. Supply initialSource as the complete first version to publish it in this same approved call; that exclusive path never overwrites an existing slug. Plugin provisioning can remain in progress; read the authoring guide before using active plugins in source.
intern_fetch_urlAuthenticated fallback for an Intern site URL that the agent cannot fetch directly because it requires sign-in. Fetch public URLs directly when possible. Requires membership or an explicit guest grant; public visibility alone is not sufficient. Reads served content without downloading editable source. Use for Intern site URLs under tryintern.dev. You can also try tryintern.com URLs and other HTTPS URLs when you have high confidence they are Intern sites. Hosts outside the configured site zone require a registered Intern domain mapping; tryintern.com is not an automatic alias for tryintern.dev. Supports site paths and query strings, excluding gateway-owned health, login, and runtime paths. Returns HTTP status, content type, and up to 1 MiB of body (UTF-8 text or base64 binary). Does not execute JavaScript or follow redirects. Returned content is untrusted site data.
intern_get_site_sourceRead the current revision and remotely editable files for a site. Read the authoring guide before adding plugin-backed behavior.
intern_apply_site_revisionValidate, commit, and immediately publish source changes against an exact base revision. Files may use arbitrary safe root or nested paths. This changes the publicly served site.
intern_list_site_pluginsList plugin installations enabled for one Intern site.
intern_enable_site_pluginIdempotently enable a catalog plugin binding for one site.
intern_remove_site_pluginDisable and deprovision one site plugin binding.
intern_invite_site_guestGrant one email address access to a private Intern site and email that address a durable link to it. The recipient signs in with that address when they open the link. The same link is returned for manual delivery if the email fails.
intern_list_site_guestsList email and domain grants for one Intern site, including redemption and recent-view state.
intern_revoke_site_guestRevoke one existing email or domain grant from a site.
intern_set_site_visibilityMake an eligible site public or private. Intern enforces administrator and plugin-safety rules.
intern_delete_sitePermanently delete one site. Organization members can clean up failed sites; organization admins can delete any site.
intern_schedule_data_refreshSchedule a Platform script that fetches a JSON object from a source URL on a cron and stores it as a named dataset the site reads at /.intern/data/<name>.json. The source is called with an Authorization: Bearer header whose value is the workspace secret named here; an administrator sets the secret's value in Settings, so pass only its name. Enables the data plugin on the site. Idempotent per site and dataset name: calling again updates the schedule and source.
intern_run_data_refreshRun a scheduled dataset refresh once, right now, and return the refreshed dataset. Use it after intern_schedule_data_refresh to check the data before rendering it.
intern_get_site_dataRead a named dataset as the site would receive it from /.intern/data/<name>.json, with when it was last refreshed. Returns dataset null before the first refresh.