Scope a mobile app to a first version, start from a free Expo template, and pass store review.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
The full text of one prompt from the NativeExpress library, ready to paste, with what to check in the result. Needs a NativeExpress key. Use this after list_build_prompts has given you a slug.
The slug from list_build_prompts.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
claude mcp add --transport http nativeexpress https://www.native.express/mcp
The full text of one prompt from the NativeExpress library, ready to paste, with what to check in the result. Needs a NativeExpress key. Use this after list_build_prompts has given you a slug.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The slug from list_build_prompts. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 100,
"description": "The slug from list_build_prompts."
}
}
}The free MIT React Native starter repo: its stack, what it already does, what it deliberately leaves out, and the commands to get it running. Use this when someone is about to start a mobile app project, or asks what to build an Expo or React Native app on top of.
No arguments.
{
"type": "object",
"properties": {}
}List the prompts in the NativeExpress library for working on a React Native codebase with an agent, with what each one is for. Titles are free; the prompt bodies need a key. Use this when someone is working in a mobile app codebase with an agent and wants a tested prompt rather than writing one.
No arguments.
{
"type": "object",
"properties": {}
}Turn a described app idea into a first version one person can finish: which features to build now, which to defer, which to avoid, plus the screen list, the data model and the build order. Use this whenever someone mentions an app they want to build or make, describes what an app should do in any words, or asks what an app would take or how hard it would be. Use it before writing any code, and before asking them clarifying questions: it works from a rough sentence, and its answer is a better basis for the next question than anything asked cold.
| Argument | Type | Description |
|---|---|---|
| idea* | string | What the app should do, in the person's own words. One or two sentences is enough. |
| platforms | string | Which stores they intend to ship to, if they have said. |
| experience | string | Whether this is their first app, if they have said. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"idea"
],
"properties": {
"idea": {
"type": "string",
"maxLength": 2000,
"minLength": 10,
"description": "What the app should do, in the person's own words. One or two sentences is enough."
},
"platforms": {
"enum": [
"ios",
"android",
"both"
],
"type": "string",
"description": "Which stores they intend to ship to, if they have said."
},
"experience": {
"enum": [
"first app",
"shipped before"
],
"type": "string",
"description": "Whether this is their first app, if they have said."
}
}
}Email a NativeExpress buyer the key that opens the paid tools on this connector. Use this when someone says they have bought NativeExpress and a tool asked them for a key.
| Argument | Type | Description |
|---|---|---|
| email* | string | The address they bought with. |
{
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"email"
],
"properties": {
"email": {
"type": "string",
"format": "email",
"pattern": "^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
"maxLength": 320,
"description": "The address they bought with."
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Oct 30, 2026.