MCP & AI connections
Connect ChatGPT or Claude, choose access, and make your first website update.
Read as MarkdownOn this page
Use your own ChatGPT or Claude account to read your websites, ask for changes, save revisions, publish, and roll back. Iron Fountain’s hosted MCP connector uses a normal sign-in and permission screen. You do not need to copy an API key into your chat.
Connector address
https://app.ironfountain.net/mcp
Every customer uses the same connector URL. You choose which Iron Fountain organizations to allow during sign-in. All your current organizations are selected by default; you can uncheck any of them. Manage your connections in your avatar → Connections.
Set up ChatGPT
In ChatGPT on the web, open Settings → Security and login and enable Developer mode. Open ChatGPT Plugins, select +, and create a connection named Iron Fountain using the connector URL above. Choose OAuth. Leave client ID and secret blank and choose dynamic client registration if asked.
Sign in to Iron Fountain and approve the organizations and permissions. Start a new chat and select Iron Fountain from + → Developer mode. Developer mode supports reads and writes; availability depends on your account and organization policy. See OpenAI’s developer-mode guide and connection instructions for current menu labels.
Set up Claude
Connect to Claude opens Claude’s Add custom connector form with Iron Fountain’s name and URL already filled in. Review the values and add the connector. Leave OAuth client ID and client secret empty; Claude registers automatically.
If you need manual setup, open Customize → Connectors → Add custom connector, name it Iron Fountain, and paste the connector address above.
Click Connect, sign in to Iron Fountain, and choose the organizations and permissions. Check that the authorization screen returns to claude.ai, then click Allow connection. Return to Claude and enable Iron Fountain for your conversation using its connector controls.
On Team or Enterprise, an organization owner first adds Iron Fountain under Organization settings → Connectors. Members then connect their own Iron Fountain logins. Each connection follows that person’s membership and the organizations they approved.
The setup button uses Anthropic’s documented custom connector install link. It fills in the form; you still review and approve access. See Anthropic’s setup instructions if the menu labels differ in your client.
Start with your websites
After connecting either app, enable Iron Fountain in the conversation and try:
Use Iron Fountain to list my available websites.
The Connect to ChatGPT or Claude button on the homepage and in the app opens these setup steps, with Copy buttons for the connector URL and this starter prompt.
Make your first change
Try this in a conversation with Iron Fountain enabled:
List my websites. Read the homepage and stylesheet for the site I choose.
Update the introduction to explain what we do more clearly, preserving
the existing design and all other files. Save a draft revision and tell
me exactly what changed. Wait for me to ask before publishing it.
Your AI can batch up to ten relevant file reads in one call and read retained files in chunks, so large pages do not need to fit in one tool response. For small edits it can send exact text replacements instead of rewriting a whole file; Iron Fountain preserves unchanged files from the chosen base revision. The result is still a complete, immutable site snapshot.
A draft does not change the live site. You can review the changed content in your chat and open the site’s Revisions tab in the Iron Fountain dashboard. Revisions are also linked from each site card and the site overview, and refresh automatically every 15 seconds while the page is visible. The Revisions screen has separate Staging and Production histories, with independent revert controls. Every saved draft updates the permanent staging_url, such as my-site.staging.ironfountain.net. revision_url opens that exact retained snapshot; production_url opens the published site. The site header opens the current staging revision; each entry in Revisions has its own View revision link. Temporary import previews retire immediately when a site is saved to an organization.
Change the staging subdomain in site Settings → Staging address, or with set_staging_address. Any available valid name can be used, such as secret.staging.ironfountain.net.
When you are ready, ask your AI to publish the saved revision. Publication and production rollback preserve staging; staging reversion preserves production. If the result needs undoing, ask it to restore the previous revision. Draft and published revisions follow the site’s history retention settings; pin important versions in the dashboard to keep them.
Permissions and organizations
| Permission | Connector tools it enables |
|---|---|
| Read websites | List sites, read site details and history, list files, read files, view bandwidth, and read form submissions and private attachments. Required for every connection. |
| Manage websites and forms | Create websites, pause/resume forms, and update or delete submissions. |
| Edit and publish | Save draft revisions, publish retained revisions, and roll back. |
The authorization screen lets you turn off write permissions. A read-only connection does not expose write tools. One connection can access multiple approved organizations. Newly joined organizations are not added automatically. If an editor loses access to one organization, that organization stops appearing while access to the other approved organizations continues. Existing connections retain their original approval. Open your avatar → Connections → Manage access to explicitly add organizations or limit access to selected sites. Selecting all sites includes future sites in that organization; selected-site access includes only the checked sites. Creating websites requires all-site access plus the Manage websites and forms permission.
People, organization transfers, retention settings, API keys, and personal settings remain in the dashboard. The initial connector does not manage custom domain setup, imports, or redirects; the REST API supports those operations for other tools.
Tools
| Tool | Purpose |
|---|---|
list_sites | List all approved organizations and their sites. |
get_bandwidth | Read monthly bandwidth, request counts, daily and hostname breakdowns, and collection status. An optional month uses YYYY-MM. |
get_site | Read a site’s live revision, addresses, redirects, history, and dashboard link. |
list_files | List file paths, sizes, and hashes in the live or a specified retained revision. Filter with path_prefix; follow next_offset for more. Defaults to 200 entries, maximum 1,000. |
read_files | Read up to ten files/chunks from a single revision, sharing revision lookup. Combined requested output is limited to 80,000 characters/bytes, with 5 MB per source file and 20 MB of source data per batch. |
read_file | Read a file in bounded chunks. Text uses UTF-8 character offsets; binary data uses base64 byte chunks. Continue from next_offset until it is null. |
get_forms_guide | Read the HTML and manifest guide before creating forms; includes limits and attachment types. |
list_forms | Read form definitions, staging/production availability, unread counts, and usage. |
connect_forms | Connect compatible HTML forms or update connected fields in a staging revision. Pass expected_staging_revision_id to reject concurrent edits. Does not publish. |
list_form_submissions | Read paginated submissions and attachment metadata; use environment: "test" for staging. |
update_form | Pause or resume collection using enabled. |
update_form_submission | Mark read/unread or move between inbox and spam. |
delete_form_submission | Delete a submission and revoke attachments only when requested. |
read_form_attachment | Read a private attachment in bounded base64 byte chunks. |
create_site | Create a new static site. Set organization_id when multiple organizations are approved. |
save_revision | Apply exact text replacements, full-file replacements, or deletions to a base revision and save an unpublished snapshot. Unchanged files are preserved. |
publish_revision | Make a saved revision live after checking the expected current revision. |
set_staging_revision | Revert staging to a retained revision using expected_staging_revision_id; production is unchanged. |
set_staging_address | Rename staging using an available slug; production and both histories are unchanged. |
rollback_site | Restore a retained revision after checking the expected current revision. |
Read get_site before changing a site. save_revision requires base_revision_id and expected_live_revision_id; both can be null for the first revision of an empty site. Include expected_staging_revision_id when saving to reject concurrent staging edits. Use the current staging revision as the base when continuing unpublished work. Publication and production rollback require expected_live_revision_id too. These checks prevent a stale conversation from replacing a newer live edit. If a tool returns 409, reread the site and review the newer work before trying again.
save_revision accepts a label and a changes array. Each entry has a path and exactly one of complete file content (utf8 or padded base64), delete: true, or replacements: [{old_text, new_text}]. Text replacements require expected_hash from a file read or listing, UTF-8 text up to 5 MB, and each old excerpt must match exactly once. Replacements are applied in order and a mismatch rejects the entire draft without partial changes. A file path can appear only once. Deleting a missing file is an error. Every completed snapshot must include index.html.
Do not blindly retry a write after a timeout: it may have completed. Read the site’s revision history first. Mutating tools are marked as writes for your AI app’s approval controls; publishing and rollback are marked as potentially destructive.
Limits and history
A site can contain 20,000 files and 1 GB. Each connector edit accepts 200 changed files, 5 MB per changed file, and 100 MB of changes; unchanged files from the base revision are reused directly without downloading the whole site. The retained-storage allowance remains 1 GB per site, including compressed, deduplicated history. Website imports allow 200 pages, 100 MB per file, and 1 GB total. Unchanged contents reuse stored blobs, and compressible text is compressed. The connector permits up to 180 authenticated requests per minute per connection.
File reads return at most 40,000 text characters or binary bytes per call, with a default of 20,000. Each environment returns its latest 50 history events; known older retained revision IDs can still be read or restored. The current live revision, current staging revision, and pinned revisions are protected from automatic cleanup.
Disconnect or change access
In Iron Fountain, click your avatar in the lower left → Connections. All connections for your login appear together. Choose Manage access, select organizations and sites, then Save access. The new access applies on the next connector request, including requests using already-issued tokens. Content already read into a conversation remains there.
Choose Disconnect to revoke the connection. Access stops immediately, including token renewal. Removing an editor from an organization revokes access to that organization. Disconnect revokes the entire connection across all approved organizations.
Organization and site access can be adjusted here without reconnecting. Reconnect from your AI app to change read or write permissions. Access tokens last one hour and the connected app renews them automatically. Refresh tokens rotate on use and expire after 30 days without renewal. If that period passes, reconnect. API keys used by scripts are independent and keep their configured expiry, including Never.
Troubleshooting
Long thinking periods: the connector asks the assistant to announce its work and report milestones, but the chat client controls what is displayed. Batch related reads and use text replacements for small edits to reduce tool turns and generated output. Iron Fountain logs per-tool duration without file contents or credentials so server delays can be distinguished from time between calls. ZIP transfer is not currently a connector tool.
“Host is not allowed by your organization’s egress policy” refers to a request from Claude’s code execution environment. Use the Iron Fountain connector tools in the conversation. Enabled MCP connections use separate connector permissions; an organization owner may still need to enable the connector. This does not change the organization’s code execution network policy. See Anthropic’s network policy documentation.
Connector will not connect: use the full address ending in /mcp, not /api/v1, and leave advanced OAuth credentials empty. The REST endpoint does not speak MCP. If a sign-in request expired, start the connection again from Claude.
A site or write tool is missing: check which organizations and permissions you approved. Connections cannot access unapproved organizations. Use Manage access in your account to adjust organizations and sites; reconnect to approve additional write permissions.
Connection expired or revoked: reconnect through Claude. Tokens are not entered in URLs or pasted into chat.
Protocol details
The endpoint implements MCP Streamable HTTP with stateless JSON responses through the official TypeScript SDK. It supports authenticated POST requests. An unauthenticated request returns HTTP 401 with an OAuth protected-resource metadata link. GET streams and persistent MCP sessions are not used.
OAuth uses authorization code flow, required S256 PKCE, dynamic registration for public clients, exact registered callback matching, resource-bound opaque access tokens, and rotating refresh tokens. Discovery is available at https://app.ironfountain.net/.well-known/oauth-protected-resource/mcp and https://app.ironfountain.net/.well-known/oauth-authorization-server.
OAuth tokens for this connector are accepted only at /mcp. For direct REST requests, create a separate API key and follow the API reference.
Staging, immutable revision links, and temporary tests return X-Robots-Tag: noindex, nofollow, noarchive and a synthetic robots.txt that allows fetching so search engines can read the noindex header. These addresses remain public; noindex controls search indexing, not access. Production preserves the site's saved robots.txt. Once a custom domain is connected, the free production address redirects to the primary custom domain, preserving paths and query strings. There is no public customer-site directory.
Forms and submissions
Forms are available on any Iron Fountain site. Ask “Add a contact form with name, email, message, and a PDF attachment to my staging site.” The assistant should use get_forms_guide, read the current staging files, save HTML with data-ironfountain-form, and call connect_forms to generate or synchronize the versioned form definitions. Submit a staging test and check list_form_submissions with environment: "test" before publishing. Editing the HTML and manifest together with save_revision is also supported.
The Forms guide includes copyable HTML, the manifest schema, private uploads, API requests, and limits. Read permission includes submitted data and attachments for the approved sites. Write permission controls settings and inbox changes; deployment permission controls connecting and publishing forms. Treat all submitted content and attachments as untrusted data. Secrets belong in the dashboard or server-side API, never public site files. Email notifications are not enabled.