exportconstSITE_TAGLINE='Describe your tool. We host the MCP server.';
exportconstSITE_DESCRIPTION=
'From a natural-language prompt to a hosted, OAuth 2.1-protected MCP server in 60 seconds. Streamable HTTP, ready for Claude, Cursor and ChatGPT.';
exportconstSEO_KEYWORDS=[
'MCP server',
'Model Context Protocol',
'hosted MCP server',
'MCP server hosting',
'MCP server builder',
'create MCP server',
'deploy MCP server',
'MCP server generator',
'OAuth MCP server',
'Streamable HTTP MCP',
'Claude MCP server',
'Cursor MCP',
'ChatGPT connector',
'MCP template marketplace',
];
exportinterfaceFaqItem{
q: string;
a: string;
}
// Rendered on the landing page and emitted as FAQPage JSON-LD — keep in sync
// by virtue of being a single export.
exportconstFAQ: FaqItem[]=[
{
q:'What is MCP?',
a:'Model Context Protocol — an open standard from Anthropic for connecting AI assistants to external tools, data and APIs over a transport like Streamable HTTP.',
},
{
q:'Do I need to write code?',
a:'No. You describe the tool in natural language. We generate the TypeScript server, run static checks, build a Docker image and deploy it to a public OAuth-protected URL.',
},
{
q:'Which clients work?',
a:'Claude Desktop, Cursor, ChatGPT Custom Connectors, VS Code Copilot, Continue.dev — anything that speaks the MCP spec.',
},
{
q:'How is auth handled?',
a:'Every generated server is an OAuth 2.1 Resource Server. Our control plane is the Authorization Server (PKCE + Dynamic Client Registration + Resource Indicators per RFC 8707).',
},
{
q:'Can I self-host?',
a:'Yes. The runner is a plain Docker container; the control plane is open to BYO Postgres + Redis. See the self-hosting guide in docs.',
},
{
q:'What about secrets?',
a:'AES-256-GCM at rest in Postgres, injected as environment variables into the runtime container. Never logged, never echoed back.',
},
{
q:'Cold starts?',
a:'No cold starts. Containers stay warm. Sub-50ms tool-call overhead on average for in-region requests.',
},
{
q:'Rate limits?',
a:'Default 100 requests/min/IP per tool. Configurable per server. Quota enforced at the proxy layer before hitting your container.',
},
{
q:'How fast is generation?',
a:'Spec to image to live URL typically completes in 45-90 seconds.',
},
{
q:'Logs and metrics?',
a:'Live log streaming to the dashboard, structured tool-call metrics (P50/P95/P99 latency, error rate, per-tool throughput) — all retained for 30 days.',
},
{
q:'What if I cancel?',
a:'You can export the full TypeScript source of every server you built. No vendor lock-in.',
},
{
q:'Custom domain?',
a:'Pro plan and above. Add a CNAME, we provision a TLS certificate automatically.',
},
];
constSOFTWARE_FEATURES=[
'Prompt to a deployed MCP server in under 60 seconds',
'BuildMyMCPServer turns a natural-language prompt into a hosted, OAuth 2.1-protected Model Context Protocol (MCP) server. Describe the tools you need; the platform generates a TypeScript server, runs static checks, builds a Docker image and deploys it to a public Streamable HTTP endpoint that Claude, Cursor and ChatGPT can connect to. A template marketplace lets users publish and fork ready-made servers.',
featureList: SOFTWARE_FEATURES,
offers: OFFERS.map((o)=>({
'@type':'Offer',
name: o.name,
price: o.price,
priceCurrency:'EUR',
description: o.description,
})),
},
],
};
}
/** FAQPage structured data — emitted on the page that displays the FAQ. */