AI that runs your whole backend
Build your backend in a conversation, from Claude Code, Cursor or the AI chat in the Anythink dashboard. The same MCP tools reach the whole CLI, from entities and fields to workflows, roles, secrets and payments.
The same task, three ways
Create a support_tickets entity and a workflow that emails the team when a ticket arrives.
The Anythink dashboard
Point and click. Good for seeing exactly what was built.
- ›Data Model → Add Entity: support_tickets
- ›Add Field: status (select)
- ›Create Entity
- ›Workflows → New Workflow: New ticket alert
- ›Trigger: a support_tickets record is created
- ›Add step: Send an Email
- ✓every new ticket emails support@example.com
The Anythink CLI
Scriptable and repeatable. Good for CI and for promoting staging to production.
$ anythink entities create support_tickets --rls$ anythink fields add support_tickets status --type varchar \--display select --options new,open,closed$ anythink workflows create "New ticket alert" \--trigger Event --entity support_tickets \--event EntityCreated --enabled$ anythink workflows step-add 61 notify-team \--action SendAnEmail --start --enabled \--params '{"to":"support@example.com","template":"new-ticket"}'- ✓Entity support_tickets created, with row-level security
- ✓Field status added
- ✓Workflow New ticket alert created and enabled
- ✓Step notify-team added
Claude, through MCP
Describe what you want, in Claude Code or the dashboard's AI chat. It runs the same commands and tells you what it did.
Why the interface can be plain text
“When the point of contact between the product and the people becomes a point of friction, then the industrial designer has failed.”
A dashboard has to be learned. An API has to be read. A conversation doesn't: you say what you want, and the Anythink MCP server carries it out, as real entities, fields and workflows. You don't have to learn Anythink before you can use it; you can describe the outcome, in your own words, and get a working system back.
One backend, reachable from plain text
The dashboard is the simple interface. The API, CLI and MCP go further: text with an AI assistant is the interface, and the output is a working system.
A hosted MCP connector, ready for Claude
Add https://mcp.anythink.cloud/mcp as a connector, sign in with your Anythink account and pick a project. Prefer to run it yourself? anythink-mcp works over stdio with Claude Code, Cursor and any other MCP client. Both reach the same commands you'd run yourself.
A tool for every CLI command
Every Anythink CLI command is its own MCP tool: entities, fields, data, workflows, roles, secrets, users, files, payments, integrations and search. Each is labelled read-only, write or destructive, so your AI client can confirm before anything risky.
The dashboard's AI chat can build too
The AI chat in the dashboard uses the same MCP tools as an external assistant. Ask it a question about your data, or ask it to create an entity, add fields or set up a workflow, and it tells you what it did, the same way Claude does anywhere else. Every change is there to check in the dashboard.
BYOK or a platform key
Each project chooses platform-managed AI usage, billed with quota tracking, or its own Claude connection for bring-your-own-key billing. Either way, the AI chat and Claude workflow steps use the project's chosen mode.
Claude and Grok as workflow steps
Claude and Grok are available as Integration steps inside a workflow, so a step can generate or transform text as part of a larger pipeline – a support ticket summarised before it's filed, a draft written before an email step sends it.
Credential changes stay local
The hosted connector signs you in with OAuth and acts only on the projects you grant. Tools that change credentials, such as login, signup, logout and switching account or config, run only in the local server, on your own machine.
Frequently Asked Questions
What is the Anythink MCP server?
The Anythink MCP server gives AI assistants a tool for every Anythink CLI command: entities, data, workflows, integrations, payments, search and more. Use it two ways: as a hosted connector at https://mcp.anythink.cloud/mcp, where you sign in with your Anythink account and choose a project, or locally with anythink-mcp over stdio for Claude Code, Cursor and other MCP clients.
Can an AI assistant do more than query data through MCP?
Yes. Beyond data reads, the generic cli tool exposes the full command surface: creating entities and fields, building and triggering workflows, managing roles and permissions, configuring secrets, and running anythink migrate between project environments.
What can the AI chat in the dashboard do?
The same things an external assistant can. It uses the Anythink MCP tools, so it can answer questions about your data and create entities, fields and workflows. It runs with Claude, using either the platform key or your project's own Claude connection.
Is it safe to expose credential changes to an AI assistant?
Yes. The hosted connector signs you in with OAuth and acts only on the projects you grant, with your own permissions. Tools that change credentials, such as login, signup, logout and switching account or config, run only in the local server on your own machine.
Can I use my own AI provider key instead of Anythink's?
Yes. A project can connect its own Claude integration and use that key for AI chat and Claude workflow steps, instead of the platform-managed key with its own usage quota.
Still have questions?
Get in TouchMore in the same project
Every feature reads from the same data model, so each one you add works with the rest.
Ways to build with it
The dashboard, the CLI, MCP and the SDK, plus guides for moving from other platforms.
Who it's for
How founders, agencies and enterprise teams use Anythink.
Documentation
Guides and reference at docs.anythink.cloud.