Your database is already most of an API.
Identities included, scoped to your agents.
Point Minimal at Postgres, MySQL, ClickHouse or a CSV — +12 more. The schema becomes endpoints. Endpoints become an MCP server. MCP becomes identity-scoped tools. Tools become agents that act on it.
Chat Studio and API Bay are in beta now, with free tiers and no card — start on selectstar.wtf.
What Agent Studio will do
Serve
The schema becomes CRUD endpoints in about five seconds, and those endpoints become MCP tools over OAuth. You never write the MCP server.
Permission
The identity you attach decides which tools the agent may call, so it touches only what you allowed.
Run
You write the job in English and grant it a tool. The target: a working agent in under 30 minutes, learning curve included.
Beta opens 14 January 2027. Open today: Chat Studio, an assistant that answers from your pages and documents. About Agent Studio →
The whole path
CSV, Parquet, XLS, JSON or NDJSON, imported as tables the moment they land. Or connect Postgres, MySQL, ClickHouse, MariaDB and 11 more — 15 databases, cloud or local, every table, view and materialized view recognized and ready to expose.
CRUD APIs — create, read, update, delete — ready in five seconds. Zero code, zero effort. For business-logic-rich APIs, describe them in chat and have them done in under five minutes — just English. Or write the Custom API yourself: code is an option here, not a requirement.
The standard way an AI assistant reaches a tool it is allowed to use — and you get your own MCP server out of the box. Choose exactly which tables and APIs to expose, then connect Claude, ChatGPT or Codex with OAuth. The AI sees only what you expose — nothing else on the server.
Roles and identities for your MCP server, defined in the UI. Assign what they can do and what they can’t — visually, with no policy files to write. Every action is permissioned.
Create agents to get any job done: answer your customers from a knowledge bank, run periodic tasks for you, and alert you the moment a number moves out of the range you set.
When the schema changes. Add a column on Monday and the endpoints follow it. They are read from the schema itself, not from a copy taken the day you connected — re-read the source and the new column reaches the API, the MCP tool and everything built on them. Nothing about the old shape is removed by the addition, so existing consumers keep working.
What’s never lost. Every call through APIs, MCP, agents and Custom API is logged, with traces exportable to any OpenTelemetry collector on self-hosted — Jaeger included. Every change to an org, project, Custom API, module or space is versioned, so an admin can roll back a dangerous one with a click. Built for endurance.
What stays with you. Authentication for your own users, third-party integrations, and logic unrelated to your database. That work is yours to build, manage and maintain.
Minimal is data access infrastructure over a database you already run. Nothing to dump, nothing to migrate — point it at your database and keep working.
Minimal supports 15 databases: Postgres, MySQL, MariaDB and ClickHouse, plus 11 more that speak their protocols — Aurora MySQL, Percona, TimescaleDB, Vitess, TiDB, CockroachDB, Citus, YugabyteDB, SingleStore, StarRocks and RisingWave. Flat files (CSV, Parquet, XLS, JSON and NDJSON) are imported as tables.
AI tools that connect to your MCP server
All eight tested against a live server. MCP is an open standard — anything that speaks it connects over OAuth.
Models your agents run on
Anthropic, OpenAI and Google built in; the open models — GLM-5 and HY3 among them — arrive through OpenCode GO.
Point Minimal at the database you already run and it serves the APIs and MCP tools, and enforces the permissions underneath. Then pick the job you want off your plate.
For site owners who answer the same visitor questions all day.
Hand it your pages and documents, publish, and one line of code puts it on your site. It answers only from what you gave it — never the model’s general knowledge.
Chatbase runs $40–$500 a month; Intercom Fin charges $0.99 per resolved conversation.
$0to start. No card, and bring your own Claude, OpenAI or Gemini key.
For anyone with a dataset and no API — and anyone who needs that data.
Drop a file; we code, host, back up and serve the endpoints. You set the price and keep all of it: 0% commission.
$1per 1,000 calls, 100 a day free. Publish from $5 a month.
For teams whose job someone still runs by hand on a schedule.
Fill in a form — name, schedule, instructions — and an agent runs it over your own database, under an identity you scope, every run audit-logged.
<30 minfrom a connection to a working agent. No code at any step.
For anyone who waits on someone else for an answer.
Ask ClickHouse or Postgres in plain English; the answer is a dashboard that keeps answering as the data moves. No extract, no copy, no warehouse in between.
36.3Mincidents across four agencies, questioned in English. No SQL.
For teams who keep asking for a tool nobody has time to build.
Describe the screens in English. The APIs behind them are generated against your live database, and desktop, installable PWA and native mobile come from one description.
10×faster to build: the API and the screens both come from one description in English.
The layer under all five. One binary serves every table of the database you already run as REST and as MCP tools, permissioned per role and audited per call. Chat Studio and API Bay were built on it.
30×less effort than hand-building the CRUD on a table, with AI or without.
Explore Minimal Core →Proof
Minimal carries Dialer, our own production app. These are its numbers.
Latency is measured server-side, which is the only part any vendor controls.
Grants — Ostrich · Sparrow · Pelican
The data layer under whatever you build — a year of it is on us.
Companies get a Minimal Core licence worth $100K to $300K: 100M to 300M requests a year on your own hardware. We take no equity and no revenue share. We ask for feedback each quarter, and that you do not build a competing product for seven years.
Sparrow puts $1M of cloud credit behind students, two-founder companies and stealth startups. Pelican gives a Minimal Core licence to non-profits that qualify, with no cap.
Nothing to migrate, nothing to install first. Bring a connection string, or start on the public NYC 911 dataset we host.
Free tier on every product, no card. Hosted, or on your own hardware.
Built from the knowledge you give it, answering visitors around the clock with no one watching it.
Point Chat Studio at your pages and documents — plus, from December 2026, the data Minimal already serves. Pick a persona: support, sales, docs, onboarding, HR and more. Hand it the knowledge. It answers from that, never the model’s general knowledge. Publish. One line puts it on your site.
In beta today. Opens the live product — sign up and test every claim on this page against your own pages.
One assistant, Acme — Onboarding Guide, the whole way.
What you just watched, stage by stage.
One assistant, start to finish
Three steps, in the order the studio walks you through them. The example the product ships with: a Support Agent answering shipping and returns questions.
Support Agent: patient, concrete, admits gaps. It answers product questions, walks through fixes, and knows when to send someone to a human. Tone layers on top — friendly & concise, precise & technical, playful — without changing what it refuses.
Paste a site’s address and tick “Read the whole site”: Minimal follows the sitemap, llms.txt and links on the same domain, up to 200 pages and the first 50,000 words of each. One page on its own gives its first 2,000 words; uploads take .txt, .md, .pdf and .docx up to 20MB each; pasted text works too.
Publishing gives you two things: a public link on your workspace domain, and an embed snippet — one line, on any page you control, whatever it’s built on: WordPress, Shopify, Webflow, or hand-rolled HTML. Nothing is visitor-reachable until you publish. Test a real question in the preview first, not in the abstract.
The assistant at the bottom right of this page was built this way. Ask it something, then read how Chat Studio works.
Coding, hosting, backups, uptime, discovery and distribution are ours. Pricing and revenue are yours — 0% commission.
Park a dataset — a flat file or a database connection. It becomes versioned REST endpoints and MCP tools, under one key. Set any price from $0.20 per 1,000 requests. Or call what others have parked, from $1 per 1,000.
Opens the live product — the first 100 requests a day on the datasets we host are free, no card.
One dataset, NYC Food Cart Calorie Data, both sides of the bay.
What you just watched, stage by stage. Every number is from the console.
One dataset, both sides of the bay
Parked by one publisher, listed in Discover, called from the playground. Every number on the three screens is from the console as it runs today.
A 1.5 MB CSV of New York City water bills, 66,432 rows, dropped on the Publish tab. Auto API derived GET /v1/apibay/nyc_water_consumption from the column types; three more datasets from the same publisher sit beside it. All 10.4 MB fits a Cove berth at $5 a month.
The same dataset in Discover, beside seven others, at the price its publisher set: $3.20 per 1,000 requests. Publisher, licence and freshness sit on the card; Try opens it in the playground.
GET https://api.selectstar.wtf/v1/apibay/nyc_water_consumption, twenty rows a page. 12.4 KB back, HTTP 200 in 828 ms. The headers price the call before you read the body: X-Cost-Per-1K: USD 3.20, this call $0.003.
Using data. Bring a key and nothing to host. Credits are loaded before they are spent, so a bill larger than the wallet you loaded cannot happen. Published datasets carry their publisher’s price, shown on the endpoint before you spend a credit.
Publishing. Bring a flat file in any of five formats, or a database connection. Parking starts at $5 a month plus $1 per 5,000 requests served; you set any price from $0.20 per 1,000 and keep 100% of it. The whole rate card.
Desktop, installable PWA and native mobile, from one description.
Point App Studio at Postgres, MySQL, ClickHouse or a CSV — 15 databases and 5 file formats. The schema becomes endpoints. Endpoints become an MCP server. Describe the screens in English — lists, forms, detail views, filters. Desktop, PWA and native mobile ship from that one description.
App Studio starts its beta on 14 January 2027. Signups open in batches of 100; everyone after joins the waitlist automatically. Chat Studio and API Bay are in beta now — start on selectstar.wtf.
What App Studio will do
Describe
Lists, forms, detail views, filters: say what each screen shows, in English.
Generate
The API behind each screen is generated against your live database, and each surface is built from that same description.
Ship
Desktop, installable PWA and native mobile come from one description. An app normally needs the API written and the screens built; here both are asked for once, which is why we say at least 10× faster than a traditional cycle.
Beta opens 14 January 2027. Open today: API Bay, hosted datasets served as priced APIs. About App Studio →
No extract. No copy. No warehouse in between.
Point Ask Studio at ClickHouse or Postgres. Ask the way you would say it out loud. The question becomes a chart. The chart pins to a dashboard. The dashboard keeps answering against the source as the data moves.
Ask Studio starts its beta on 14 January 2027. Signups open in batches of 100; everyone after joins the waitlist automatically. Chat Studio and API Bay are in beta now — start on selectstar.wtf.
What Ask Studio will do
Ask
Point Ask Studio at ClickHouse or Postgres and ask in plain English.
Chart
The question becomes a chart, and the chart pins to a dashboard.
Keep
The dashboard keeps answering against the source as the data moves. Nothing is extracted and nothing is duplicated.
Beta opens 14 January 2027. Open today: Chat Studio, the same plain-English idea for your website visitors. About Ask Studio →