Superwall MCP server, with a policy gate.
Scope-typed paywall access for AI agents: Gentkey maps the official Superwall MCP server's 52 live-enumerated tools to the API scopes Superwall's own spec assigns them — 17 free reads, 34 scope-typed grants (28 writes, 6 gated reads), and organization creation held behind the full grant — so an agent that builds paywalls can't touch campaigns, or your webhooks.
https://app.gentkey.com/mcpclaude.ai (web & mobile) · Claude Code · Cursor · any MCP clientWhat’s free, what needs a grant.
Reads: Browsing projects, paywalls, campaigns, entitlements, products, and chart data works with no grant — 17 curated read tools. Webhook configs and raw analytics SQL stay grant-gated: delivery logs replay event payloads, and “read-only” SQL is Superwall's word, not an enforced property.
Writes: 34 tools map to grants mirroring Superwall's own API scopes — 28 writes plus 6 grant-gated reads (webhook configs and raw SQL) — curated against the live-enumerated 52-tool inventory. Anything Superwall ships later fails closed to the full write grant.
Gentkey proxies the official Superwall MCP server (https://superwall-mcp.superwall.com/mcp) — you get the vendor’s own tools, with custody, gating, and audit added in front.
| Grant | What it governs |
|---|---|
mcp-superwall.projects.write | Creating, updating, archiving projects and adding apps |
mcp-superwall.applications.write | App settings — including the credentials they carry (Stripe key, App Store Connect shared secret) |
mcp-superwall.entitlements.write | Entitlement changes |
mcp-superwall.products.write | Product changes |
mcp-superwall.paywalls.write | Paywall creation, duplication, archive and unarchive — there's no edit tool upstream; editing lives in Superwall's separate editor surface |
mcp-superwall.campaigns.write | Campaign and placement changes |
mcp-superwall.webhooks.read | Webhook configs and delivery logs — gated because configs carry secrets and logs replay payloads |
mcp-superwall.webhooks.write | Creating and editing webhooks — an egress channel |
mcp-superwall.data.read | Raw ClickHouse analytics SQL — read-only on Superwall's word alone, so it's a grant |
mcp-superwall.write | Everything unmapped, including account-level organization creation |
Connect once, use everywhere.
Sign in at gentkey.com, add Superwall (oauth), then point each client at your endpoint. Every client completes a standard OAuth flow and lands in your Gentkey — your connections, nobody else’s.
claude.ai (web & mobile)
- Settings → Connectors
- Add custom connector
- Paste
https://app.gentkey.com/mcpand finish the OAuth prompt
Claude Code
claude mcp add --transport http \
gentkey https://app.gentkey.com/mcpCursor
// .cursor/mcp.json
{
"mcpServers": {
"gentkey": { "url": "https://app.gentkey.com/mcp" }
}
}Things agents do with Superwall here.
- How did paywall conversion change after last week's edit?
- List the active campaigns and their placements.
- Duplicate the onboarding paywall so I can try a July variant.
- Which products are attached to the annual entitlement?
Custody, gating, and audit — built in.
The model never sees a credential
Your Superwall token is encrypted at rest and injected server-side at call time. Your stored credential never enters a context window.
Writes need a grant
Anything that changes state needs a capability you granted explicitly — revoke it and the next call is denied.
A trail you can act on
Every decision is attributed to the agent that made it — allowed, denied, or denied by constraint.
Fair questions.
Why is chart data a free read but analytics SQL a grant?
get_chart_data sends a closed, enumerated query — it can only ask predefined questions. run_clickhouse_query proxies arbitrary SQL that is read-only on Superwall's word alone, so Gentkey keeps it behind mcp-superwall.data.read instead of trusting the label.
What happens when an agent calls a Superwall write tool it hasn't been granted?
The call is denied at the gateway — nothing reaches Superwall — and the denial is recorded in the audit log along with the grant that would have authorized it, so you can decide deliberately instead of finding out later.
Where are my credentials stored?
Encrypted at rest (AES-256-GCM) on Gentkey's server and injected server-side at call time. No credential you store with Gentkey ever enters a model's context window or an agent's config file.
Can I use this from claude.ai's free plan?
Yes — and it's the strongest case for a gateway: free claude.ai accounts currently get a single custom connector, so pointing that one slot at Gentkey puts every connector you've linked behind it.
How do I revoke an agent's access?
Revoke the grant (the next write is denied) or revoke the agent's tokens entirely in one click. Other agents and their grants are untouched — no shared key to rotate.
Is Gentkey affiliated with Superwall?
No. Gentkey is an independent MCP gateway. Trademarks belong to their owners; where an official Superwall MCP server exists, Gentkey proxies it and adds custody, gating, and audit on top.
Often connected together.
Cut Superwall a smaller key.
Sign in, connect Superwall, and grant your first scoped capability in under a minute.