Dataceen
Remote MCP server that turns a business description into a data model, API and hosted app
- Pricing
- Free trial
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 1 day ago
About Dataceen
Dataceen is an MCP server for developer tools. It runs as a hosted remote server, so there is nothing to install locally.
The assistant drafts a data model from a sentence, a page, an OpenAPI spec, a database schema, an AsyncAPI document, a document or an image. The user sees it as a picture, asks for changes in conversation and approves it, after which Dataceen creates a database per model, a GraphQL API, search, events, SDKs in six languages, documentation and an MCP server of its own.
Publishing is done by scope: each scope decides what a consumer may see and change, and gets its own MCP server and API. An application such as a dashboard, site or task program can be built and hosted, with code in a private GitHub repository that can be shared or transferred.
A guest can draft models without an account, kept for 30 days. AI work is paid in credits, where one credit is one euro cent, with an estimate before each build and nothing charged for a failed run. Plans start with a 14-day free trial, then Studio at 79 euros per developer per month and production per model at 249 euros. Data is stored in the EU.
Install
Run in a terminal
claude mcp add --transport http dataceen https://mcp.dataceen.com/mcp/studioAdd to Settings → Connectors → Add custom connector
https://mcp.dataceen.com/mcp/studioAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"dataceen": {
"url": "https://mcp.dataceen.com/mcp/studio"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"dataceen": {
"type": "http",
"url": "https://mcp.dataceen.com/mcp/studio"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"dataceen": {
"serverUrl": "https://mcp.dataceen.com/mcp/studio"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"dataceen": {
"type": "http",
"url": "https://mcp.dataceen.com/mcp/studio"
}
}
}Tools this server provides (19)
Taken from the project documentation; the running server may differ.
- about_dataceen
- Facts about Dataceen.
- create_model
- Starts a model with a name.
- add_source
- Adds text, a spec, schema, document or image as a source.
- remove_source
- Removes a source.
- build_model
- Drafts the model from the sources.
- get_model
- Returns entities, relationships, scopes and a picture link.
- update_model
- Changes a created model.
- create_system
- Creates the reviewed model as a running system.
- generate_example_data
- Fills the system with example records.
- update_scope
- Decides what a consumer sees and may change.
- publish
- Makes a scope live as its own MCP server and API.
- get_sdk
- Returns the SDK in a chosen language.
- build_application
- Builds and hosts an application.
- get_application
- Returns application state, address and code.
- change_application
- Changes the live application.
- take_down_application
- Takes an application offline.
- share_repository
- Invites a GitHub user to the repository.
- transfer_repository
- Transfers the repository.
- get_balance
- Shows credits and build estimates.
What it does
- Model drafting
- Drafts a data model from text, specs, schemas or images.
- Generated system
- Creates databases, a GraphQL API, search, events and SDKs in six languages.
- Scoped publishing
- Publishes each consumer scope as its own MCP server and API.
- Hosted applications
- Builds and hosts dashboards, sites or task programs.
- Own your code
- Keeps code in a private GitHub repository you can take over.
- Credit estimates
- Shows an estimate before every build; failed runs cost nothing.
Good for
- Draft a data model for a field-service company from one prompt
- Generate an API and SDK from a described business
- Publish a read-only scope for one consumer
- Build a dashboard on the generated system
Pricing
Free trial
14-day free trial; Studio EUR 79/developer/month; production EUR 249/model/month
Prices change. Check dataceen.com before you buy.
Dataceen FAQ
Do I need an account?
No. A guest can draft models for 30 days, and a free account is needed to create the system.
How is AI work charged?
In credits at one euro cent each; every build shows an estimate and failed runs cost nothing.
What does it cost?
A 14-day free trial, then Studio at 79 euros per developer per month; production per model is 249 euros.
Where is data stored?
In the EU, per the site.
Is Dataceen free?
Dataceen is a paid product with a free trial.
How do I add Dataceen to Claude Code?
Run this command in your terminal: claude mcp add --transport http dataceen https://mcp.dataceen.com/mcp/studio
What are the best alternatives to Dataceen?
The closest alternatives to Dataceen are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Dataceen

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools