Bkend Quickstart logo

Bkend Quickstart

Organization
ww-w-ai
bkend-quickstart

bkend.ai platform onboarding and core concepts guide. Covers MCP setup, resource hierarchy (Org->Project->Environment), Tenant vs User model, and first project creation. Use proactively when user is new to bkend or asks about initial setup. Triggers: bkend setup, first project, bkend start, MCP connect, bkend 시작, 처음, 설정, MCP 연결, 프로젝트 생성, bkend始め方, 初期設定, MCP接続, bkend入门, 初始设置, MCP连接, configuracion bkend, primer proyecto, configuration bkend, premier projet, bkend Einrichtung, erstes Projekt, configurazione bkend, primo progetto Do NOT use for: advanced auth flows (use bkend-auth), database queries (use bkend-data), file storage (use bkend-storage), security policies (use bkend-security)

Overview

Publisherww-w-ai
Repositorybkit-gemini
Skill namebkend-quickstart
Stars
66
Forks
16
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ww-w-ai on GitHub. Read the source before you install it.

Installation

Install the Bkend Quickstart AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ww-w-ai/bkit-gemini.git /tmp/bkit-gemini
mkdir -p .claude/skills
cp -r /tmp/bkit-gemini/skills/bkend-quickstart .claude/skills/bkend-quickstart
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bkend Quickstart in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bkend Quickstart on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bkend Quickstart is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

bkend-quickstart

bkend.ai platform onboarding and core concepts guide

1. What is bkend.ai

bkend.ai is a Backend-as-a-Service (BaaS) platform built on MongoDB Atlas. It provides:

  • REST API endpoints for CRUD operations, authentication, file storage, and more
  • MCP (Model Context Protocol) server for AI-assisted development with Gemini CLI, Claude Code, and Cursor
  • Console UI at https://console.bkend.ai for visual management
  • Zero-config database powered by MongoDB Atlas (no schema migration needed)
  • Multi-tenant architecture with project-level isolation

Key Differentiators

Featurebkend.aiTraditional BaaS
AI IntegrationNative MCP supportNone
DatabaseMongoDB Atlas (managed)Self-managed
SchemaSchemaless / flexibleRigid migrations
AuthBuilt-in JWT + SocialPlugin-based
File StorageIntegratedSeparate service

2. Core Concepts

2.1 Resource Hierarchy

Organization (Org)
└── Project
    └── Environment (dev / staging / prod)
        ├── Tables (collections)
        ├── Auth (users, sessions)
        ├── Storage (files, buckets)
        └── API Keys
  • Organization: Top-level billing and team boundary. One user can belong to multiple orgs.
  • Project: A single application or service. Contains its own database, auth, and storage.
  • Environment: Isolated runtime context within a project. Each environment has its own data, API keys, and configuration. Default environments: dev, staging, prod.

2.2 Tenant vs User Model

bkend.ai distinguishes between two identity layers:

ConceptTenantUser
WhoDeveloper / team memberEnd-user of your app
ScopeConsole + API managementApp-level auth
AuthConsole login/auth/* endpoints
PermissionsOrg/Project rolesRBAC (admin/user/self/guest)
API KeyYes (X-API-Key)No (uses JWT)
  • Tenant: You, the developer. Manages projects via the Console or API keys.
  • User: Your application's end-user. Authenticates via email, social login, or magic link.

2.3 API Structure

Base URL:

https://api-client.bkend.ai

MCP URL:

https://api.bkend.ai/mcp

Required Headers for all API calls:

http
X-Project-Id: <your-project-id>
X-Environment: <dev|staging|prod>

Authentication Headers (choose one):

http
# For tenant/server-side calls
X-API-Key: <your-api-key>

# For user-authenticated calls
Authorization: Bearer <access-token>

Standard Response Format:

json
{
  "success": true,
  "data": { ... },
  "meta": {
    "page": 1,
    "limit": 20,
    "total": 100
  }
}

Standard Error Format:

json
{
  "success": false,
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "Invalid email format",
    "details": [...]
  }
}

3. Quick Start Steps

Step 1: Sign Up

Visit https://console.bkend.ai/signup and create your tenant account.

Step 2: Create an Organization

http
POST https://api-client.bkend.ai/orgs
Content-Type: application/json

{
  "name": "My Company",
  "slug": "my-company"
}

Or use the Console: Dashboard > Create Organization.

Step 3: Create a Project

http
POST https://api-client.bkend.ai/projects
Content-Type: application/json
X-Org-Id: <your-org-id>

{
  "name": "My App",
  "slug": "my-app"
}

Or use the Console: Organization > New Project.

Step 4: Set Environment

Each project starts with three environments: dev, staging, prod. Choose your target:

http
X-Project-Id: proj_abc123
X-Environment: dev

Step 5: Create a Table

http
POST https://api-client.bkend.ai/tables
Content-Type: application/json
X-Project-Id: proj_abc123
X-Environment: dev
X-API-Key: <your-api-key>

{
  "name": "todos",
  "schema": {
    "title": { "type": "string", "required": true },
    "completed": { "type": "boolean", "default": false },
    "priority": { "type": "number", "default": 0 }
  }
}

Step 6: Get an API Key

Navigate to Console > Project > Settings > API Keys and generate a new key. Or via API:

http
POST https://api-client.bkend.ai/api-keys
X-Project-Id: proj_abc123
X-Environment: dev

Step 7: Call the API

bash
# Create a record
curl -X POST https://api-client.bkend.ai/data/todos \
  -H "Content-Type: application/json" \
  -H "X-Project-Id: proj_abc123" \
  -H "X-Environment: dev" \
  -H "X-API-Key: your-api-key" \
  -d '{"title": "Learn bkend", "completed": false}'

# List records
curl https://api-client.bkend.ai/data/todos \
  -H "X-Project-Id: proj_abc123" \
  -H "X-Environment: dev" \
  -H "X-API-Key: your-api-key"

4. MCP Setup

4.1 Gemini CLI

Create or edit ~/.gemini/settings.json:

json
{
  "mcpServers": {
    "bkend": {
      "httpUrl": "https://api.bkend.ai/mcp",
      "headers": {
        "X-Project-Id": "proj_abc123",
        "X-Environment": "dev",
        "X-API-Key": "your-api-key"
      }
    }
  }
}

After setup, restart Gemini CLI. You can then use natural language:

> Create a users table with name, email, and age fields
> Add a new user named Alice with email alice@example.com
> List all users where age > 25

4.2 Claude Code

Create or edit .mcp.json in your project root:

json
{
  "mcpServers": {
    "bkend": {
      "type": "http",
      "url": "https://api.bkend.ai/mcp",
      "headers": {
        "X-Project-Id": "proj_abc123",
        "X-Environment": "dev",
        "X-API-Key": "your-api-key"
      }
    }
  }
}

4.3 Cursor

Open Cursor Settings > MCP Servers and add:

json
{
  "bkend": {
    "type": "http",
    "url": "https://api.bkend.ai/mcp",
    "headers": {
      "X-Project-Id": "proj_abc123",
      "X-Environment": "dev",
      "X-API-Key": "your-api-key"
    }
  }
}

5. Framework Quick Start

5.1 Next.js Setup

Environment Variables (.env.local):

env
NEXT_PUBLIC_BKEND_API_URL=https://api-client.bkend.ai
NEXT_PUBLIC_BKEND_PROJECT_ID=proj_abc123
NEXT_PUBLIC_BKEND_ENVIRONMENT=dev
BKEND_API_KEY=your-api-key

bkendFetch Client (lib/bkend.ts):

typescript
interface BkendFetchOptions extends RequestInit {
  token?: string;
}

export async function bkendFetch<T = any>(
  path: string,
  options: BkendFetchOptions = {}
): Promise<T> {
  const { token, headers: customHeaders, ...rest } = options;

  const headers: Record<string, string> = {
    "Content-Type": "application/json",
    "X-Project-Id": process.env.NEXT_PUBLIC_BKEND_PROJECT_ID!,
    "X-Environment": process.env.NEXT_PUBLIC_BKEND_ENVIRONMENT!,
    ...customHeaders as Record<string, string>,
  };

  // Server-side: use API key
  if (typeof window === "undefined" && process.env.BKEND_API_KEY) {
    headers["X-API-Key"] = process.env.BKEND_API_KEY;
  }

  // Client-side: use JWT token
  if (token) {
    headers["Authorization"] = `Bearer ${token}`;
  }

  const res = await fetch(
    `${process.env.NEXT_PUBLIC_BKEND_API_URL}${path}`,
    { headers, ...rest }
  );

  if (!res.ok) {
    const error = await res.json();
    throw new Error(error.error?.message || "bkend API error");
  }

  return res.json();
}

Middleware (middleware.ts):

typescript
import { NextRequest, NextResponse } from "next/server";

export async function middleware(request: NextRequest) {
  const accessToken = request.cookies.get("bkend_access_token")?.value;
  const refreshToken = request.cookies.get("bkend_refresh_token")?.value;

  // Public routes - skip auth
  const publicPaths = ["/login", "/signup", "/"];
  if (publicPaths.includes(request.nextUrl.pathname)) {
    return NextResponse.next();
  }

  if (!accessToken && !refreshToken) {
    return NextResponse.redirect(new URL("/login", request.url));
  }

  // Auto-refresh if access token is missing but refresh token exists
  if (!accessToken && refreshToken) {
    try {
      const res = await fetch(
        `${process.env.NEXT_PUBLIC_BKEND_API_URL}/auth/token/refresh`,
        {
          method: "POST",
          headers: {
            "Content-Type": "application/json",
            "X-Project-Id": process.env.NEXT_PUBLIC_BKEND_PROJECT_ID!,
            "X-Environment": process.env.NEXT_PUBLIC_BKEND_ENVIRONMENT!,
          },
          body: JSON.stringify({ refreshToken }),
        }
      );

      if (res.ok) {
        const data = await res.json();
        const response = NextResponse.next();
        response.cookies.set("bkend_access_token", data.data.accessToken, {
          httpOnly: true,
          secure: true,
          sameSite: "lax",
          maxAge: 3600,
        });
        return response;
      }
    } catch {
      return NextResponse.redirect(new URL("/login", request.url));
    }
  }

  return NextResponse.next();
}

export const config = {
  matcher: ["/((?!_next/static|_next/image|favicon.ico).*)"],
};

5.2 Flutter Setup

DioClient (lib/core/network/bkend_client.dart):

dart
import 'package:dio/dio.dart';

class BkendClient {
  late final Dio _dio;

  BkendClient({
    required String projectId,
    required String environment,
    String? apiKey,
  }) {
    _dio = Dio(BaseOptions(
      baseUrl: 'https://api-client.bkend.ai',
      headers: {
        'Content-Type': 'application/json',
        'X-Project-Id': projectId,
        'X-Environment': environment,
        if (apiKey != null) 'X-API-Key': apiKey,
      },
    ));

    _dio.interceptors.add(AuthInterceptor());
  }

  Future<Response<T>> get<T>(String path, {
    Map<String, dynamic>? queryParameters,
  }) => _dio.get<T>(path, queryParameters: queryParameters);

  Future<Response<T>> post<T>(String path, {dynamic data}) =>
      _dio.post<T>(path, data: data);

  Future<Response<T>> put<T>(String path, {dynamic data}) =>
      _dio.put<T>(path, data: data);

  Future<Response<T>> delete<T>(String path) => _dio.delete<T>(path);
}

Auth Interceptor (lib/core/network/auth_interceptor.dart):

dart
import 'package:dio/dio.dart';
import 'package:flutter_secure_storage/flutter_secure_storage.dart';

class AuthInterceptor extends Interceptor {
  final _storage = const FlutterSecureStorage();

  
  void onRequest(RequestOptions options, RequestInterceptorHandler handler) async {
    final token = await _storage.read(key: 'access_token');
    if (token != null) {
      options.headers['Authorization'] = 'Bearer $token';
    }
    handler.next(options);
  }

  
  void onError(DioException err, ErrorInterceptorHandler handler) async {
    if (err.response?.statusCode == 401) {
      final refreshToken = await _storage.read(key: 'refresh_token');
      if (refreshToken != null) {
        try {
          final dio = Dio();
          final res = await dio.post(
            'https://api-client.bkend.ai/auth/token/refresh',
            data: {'refreshToken': refreshToken},
            options: Options(headers: err.requestOptions.headers),
          );
          final newToken = res.data['data']['accessToken'];
          await _storage.write(key: 'access_token', value: newToken);

          // Retry original request
          err.requestOptions.headers['Authorization'] = 'Bearer $newToken';
          final retryRes = await dio.fetch(err.requestOptions);
          handler.resolve(retryRes);
          return;
        } catch (_) {
          await _storage.deleteAll();
        }
      }
    }
    handler.next(err);
  }
}

6. Console Guide Summary

The bkend.ai Console (https://console.bkend.ai) provides visual management for all platform features:

SectionDescription
ProjectsCreate, configure, and manage projects
EnvironmentsSwitch between dev/staging/prod environments
TablesCreate collections, define schemas, browse data
API KeysGenerate and revoke API keys per environment
AuthView registered users, manage sessions
StorageBrowse uploaded files, manage buckets
TeamInvite members, assign roles (Owner/Admin/Member)
SettingsProject configuration, custom domains, webhooks
LogsView API request logs and error traces

7. Environment Variables Reference

VariableRequiredDescriptionExample
NEXT_PUBLIC_BKEND_API_URLYesbkend API base URLhttps://api-client.bkend.ai
NEXT_PUBLIC_BKEND_PROJECT_IDYesYour project IDproj_abc123
NEXT_PUBLIC_BKEND_ENVIRONMENTYesTarget environmentdev
BKEND_API_KEYServer onlyAPI key for server-side callsbk_key_...
NEXT_PUBLIC_BKEND_MCP_URLOptionalMCP server URLhttps://api.bkend.ai/mcp
BKEND_WEBHOOK_SECRETOptionalWebhook signature secretwhsec_...
NEXT_PUBLIC_GOOGLE_CLIENT_IDOptionalGoogle OAuth client ID123...apps.googleusercontent.com
NEXT_PUBLIC_GITHUB_CLIENT_IDOptionalGitHub OAuth client IDgh_abc123

8. Next Steps

Once you have completed setup, use the following bkend-* skills for each domain:

DomainSkillDescription
Authentication/bkend-authEmail/social login, JWT, sessions, RBAC, MFA
Data Operations/bkend-dataCRUD, queries, filtering, pagination, relations
File Storage/bkend-storageUpload, download, presigned URLs, image transforms
Security/bkend-securityRLS policies, rate limiting, CORS, audit logs
MCP Tools/bkend-mcpMCP server tools reference and advanced usage
Realtime/bkend-realtimeWebSocket subscriptions, live queries
Functions/bkend-functionsServer-side functions, webhooks, scheduled tasks

Recommended Learning Path

  1. Start here (bkend-quickstart) -- you are here
  2. Authentication (/bkend-auth) -- set up user auth for your app
  3. Data Operations (/bkend-data) -- CRUD and query patterns
  4. Storage (/bkend-storage) -- file uploads and management
  5. Security (/bkend-security) -- production-ready security policies

Frequently asked questions

What does the Bkend Quickstart AI skill do?

bkend.ai platform onboarding and core concepts guide. Covers MCP setup, resource hierarchy (Org->Project->Environment), Tenant vs User model, and first project creation. Use proactively when user is new to bkend or asks about initial setup. Triggers: bkend setup, first project, bkend start, MCP connect, bkend 시작, 처음, 설정, MCP 연결, 프로젝트 생성, bkend始め方, 初期設定, MCP接続, bkend入门, 初始设置, MCP连接, configuracion bkend, primer proyecto, configuration bkend, premier projet, bkend Einrichtung, erstes Projekt, configurazione bkend, primo progetto Do NOT use for: advanced auth flows (use bkend-auth), database qu...

Why use Bkend Quickstart on TypingMind?

Because you install it once and use it with any model. Bkend Quickstart is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bkend Quickstart in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ww-w-ai/bkit-gemini/tree/main/skills/bkend-quickstart. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bkend Quickstart?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bkend Quickstart?

As many as you like. As long as a model supports skills, you can use Bkend Quickstart with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bkend Quickstart AI skill free?

Yes. It is published on GitHub by ww-w-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇