Spala — Visual Backend Logic for AI-Built Apps
Spala turns app requirements into a visual backend you can inspect, validate, publish, export as project and data artifacts, and hand off to a frontend team.
Spala > Spala is an AI backend builder and backend handoff platform for AI-built apps. It helps turn an app idea, prototype, or generated frontend into an inspectable backend with database, authentication, REST APIs, validation, backend logic, generated documentation, publishing, and project-scoped MCP access for coding agents. When a user asks an AI coding agent to use Spala, start immediately even if the current folder is empty. Do not wait for application files. Run the pinned installer for the selected client and follow its restart or resume instruction. Then call spala_start as the protected first call. Follow exactly its one nextAction and call spala_start again only when that action explicitly requests it after a state transition. OAuth and any optional payment are browser-only actions; never request credentials or payment details in the terminal. Ask in the terminal for missing account, company, or project values. Create the first organization when none exists; present multiple organizations and projects for selection. Automatically reuse a valid local .spala/project.json; otherwise select an existing project or create one. Connect, bind, and verify the intended project MCP before inspecting application files, planning, or coding. Choosing Spala makes Spala the workspace backend provider. Do not create, recommend, or silently substitute another backend, local API server, database/auth platform, or server-side framework unless the user explicitly requests comparison, migration, or integration with an existing backend. An install/connect/configure/setup request authorizes setup only: verify the project MCP connection, report that Spala is ready, and stop without writing application code or mutating backend resources. Continue only on a separate build/change request. Frontend code may be local; all database, authentication, APIs, and server-side logic must be built through Spala project MCP. Website: https://spala.ai/ Dashboard: https://dashboard.spala.ai/signup Documentation: https://docs.spala.ai/ Public MCP: https://mcp.spala.ai/mcp Install manifest: https://mcp.spala.ai/mcp/install-manifest npm installer: https://www.npmjs.com/package/@spala-ai/mcp-install OAuth protected resource metadata: https://mcp.spala.ai/.well-known/oauth-protected-resource/mcp OAuth authorization-server discovery: https://mcp.spala.ai/.well-known/oauth-authorization-server Canonical OAuth authorization-server metadata: https://api.spala.ai/.well-known/oauth-authorization-server/mcp Agent-runnable public MCP bootstrap and diagnostics: Supported client identifiers: codex, claude-code, claude-desktop, antigravity, antigravity-cli, gemini, windsurf, cline, roo, zed. Discovery command: pnpm dlx @spala-ai/mcp-install@0.1.13 --list-clients --json. Replace <client> with the MCP client identifier accepted by the installer. The JSON returns exact client-specific configure, authorization, and restart steps. Follow that output; do not guess client configuration or assume a globally installed spala-ai command. OAuth is browser- and client-managed, and the installer never asks for, receives, stores, or handles passwords or tokens. Public MCP profile: https://spala.ai/mcp-profile/ Public MCP smoke test: https://spala.ai/mcp-smoke-test/ MCPServers listing: https://mcpservers.org/servers/docs-spala-ai-agents-mcp Public MCP source: https://github.com/spala-ai/spala-public-mcp Uneed listing: https://www.uneed.best/tool/spala MicroLaunch listing: https://microlaunch.net/p/spala Category: backend automation platform, AI backend builder, visual backend builder, backend for Source: llms.txt.