mcpField
A
AutoSugges

AutoSugges

Local
autosugges.comDeveloper Tools0Updated 6d ago

About AutoSugges

AutoSugges is an autocomplete API and UI library for developers building forms with reference lists. It provides edge-served data and components for React, React Native, and plain HTML.

Key features

  1. 01Autocomplete for reference datasets
  2. 02React and Next.js components
  3. 03React Native UI components
  4. 04Plain HTML integration
  5. 05Server-defined selection behavior

Use cases

  1. 01Add country or airport fields to a form
  2. 02Offer NAICS or currency suggestions
  3. 03Build multi-select reference-list inputs

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"autosugges-autosugges": {
"command": "npx",
"args": [
"-y",
"@autosugges/mcp"
],
"env": {
"AUTOSUGGES_PUBLISHABLE_KEY": "<AUTOSUGGES_PUBLISHABLE_KEY>",
"AUTOSUGGES_RUNTIME_URL": "<AUTOSUGGES_RUNTIME_URL>"
}
}
}
}
Run commandnpx -y @autosugges/mcp
Environment variables to set
AUTOSUGGES_PUBLISHABLE_KEYSecretPublishable key (pk_live_...) for the list to search. Free at https://app.autosugges.com. Required for search_list.
AUTOSUGGES_RUNTIME_URLRuntime origin.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@autosugges/mcp0.1.1

Tools

4

Saved tool list · updated 5d ago

ParameterTypeRequiredDescription
liststringNoInformational list name or slug. The configured key selects the list.
limitintegerNoMax suggestions; capped by the list policy.
querystringYesText typed so far; at least 2 characters.
localestringNoBCP-47 tag for display values, e.g. "fr".
parentstringNoItem id of a parent (hierarchical lists only), to restrict to its descendants.

Details

From the project README

@autosugges/client

AutoSugges: edge autocomplete API + free reference datasets (countries, NAICS, airports, currencies…) behind one React / React Native / HTML component.

npm license

Docs: https://docs.autosugges.com · Datasets: https://autosugges.com

npm i @autosugges/client

Replace YOUR_PUBLISHABLE_KEY with a free key from https://app.autosugges.com — one key per list, locked to your site's origins. Publishable keys are safe in a browser.

React / Next.js

'use client';
import { useState } from 'react';
import { AutoSugges } from '@autosugges/client/react';
import { AutosuggesProvider, type AutoSuggesValue } from '@autosugges/client/react-core';

export function CountryField() {
  const [country, setCountry] = useState<AutoSuggesValue>(null);
  return (
    <AutosuggesProvider lists={{ countries: 'YOUR_PUBLISHABLE_KEY' }}>
      <AutoSugges list="countries" value={country} onChange={setCountry} />
    </AutosuggesProvider>
  );
}

value is the full selected item (an array for multi-select lists). Behaviour — minimum characters, debounce, creatable items, multi-select — comes from the list's server policy; overrides can only narrow it.

Expo / React Native

import { AutoSugges } from '@autosugges/client/native-ui';
import { AutosuggesProvider } from '@autosugges/client/react-core';
// same props as web: <AutoSugges list="countries" value={value} onChange={setValue} />

Optional peers for the bottom-sheet presentation: @gorhom/bottom-sheet, react-native-gesture-handler, react-native-reanimated.

Plain HTML

<script src="https://cdn.jsdelivr.net/npm/@autosugges/client/dist/browser/autosugges.js"></script>
<input
  data-autosugges-key="YOUR_PUBLISHABLE_KEY"
  data-autosugges-base-url="https://runtime.autosugges.com"
  data-autosugges-placeholder="Country"
/>

Self-hosted copy with an SRI hash: https://autosugges.com/sdk/v1/autosugges.js. Other attributes: data-autosugges-theme (light|dark), -locale, -label, -parent, -access-token. Call window.AutoSugges.autoInit() after injecting markup later.

Entry points

. (client, combobox state machine) · ./react · ./react-core · ./native · ./native-ui · ./browser. Style it with CSS custom properties (--as-color-text, --as-font-sans, …); see the docs.

MIT © AKHBaig

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.