Monthly Cohort — the first 100 early-access sign-ups, plus the first 60 every month after launch, get their first month freePersonal plans COHORT60
InventDB Serverless · a real database your AI agent can run

A real database your AI agent can run.

Give the agent you already use — Claude Desktop, Hermes Agent, or OpenClaw — a real, private database it runs over MCP: flexible, encrypted, searchable, and yours. It files your receipts, totals your spending, hands you a report — things a chat can't. Underneath it's a serious database: full SQL, ACID, on your own encrypted volume, scaling to 250M records for the software you build. No AI in the box — the intelligence is your agent's.

From $11/mo· Up to 250M records· Single server
Four surfaces, one database

Bring your AI. Write SQL. Administer the rest.

Every InventDB Serverless instance gives you four ways to work the same private database — the one you bring (your AI agent, over MCP), plus three built in: a SQL Studio to write and run SQL by hand, a Files browser to search every attachment by name, by the text inside it, or by meaning, and an Engine to administer it. The three built-in surfaces run no AI — the intelligence is whatever agent you point at it.

AI Agent

Bring your own AI, over MCP

The surface you bring. Point Claude Desktop, Hermes Agent, or OpenClaw at your database over MCP, and it reads, writes, searches and reports through 51 safe, typed tools — bounded by your role and row rules, every call logged. Below: Claude Desktop rendering a real owner statement straight from the ledger.

Claude Desktop connected to an InventDB database over MCP — it queried a property owner's ledger, reconciled Q4 2026, and rendered an owner statement showing $46,830 operating income, $8,520 expenses and $38,309.52 net owner distribution.
Claude Desktop over MCP — a real query, a real report, from your own database.

Bring your own:the intelligence is your agent's — InventDB ships no AI in the box; it's the private database the agent runs.

SQL Studio

Write and run SQL by hand

A workbench, not a chatbot. Browse the schema of your namespaces, types and columns, write SQL in the editor and run it — a results grid, query history, and Download CSV / JSON.

your-db.inventdb.cloud / sql
SQL Studio: a schema browser of namespaces, types and columns; a hand-written SQL editor; a results grid; query history; and Download CSV / JSON. No AI assistant — just the database.
SQL Studio over their own server — write-and-run SQL by hand. AI-free.

AI-free:no AI assistant in this build; the /sql endpoint is open for your own tools and for external AI agents over MCP.

Files

Find any file, one place

Every attachment across all your namespaces and types in one drive. Walk the folder tree, or search by filename, by the text inside a file, or by meaning — full-text and semantic search over PDFs, images and documents, with OCR built in.

your-db.inventdb.cloud / files
Files: a global drive across every namespace and type — a folder tree, a file grid showing each file's home, and search by name, by the text inside files, or by meaning over OCR'd documents.
Files — every attachment in one place, searchable by name, text, or meaning.

AI-free:text and semantic search run on the OCR and embedding models built into the database — no external AI needed.

Engine

Administer the database

The admin surface: Relationships, Data Quality, Search Freshness, Attachment Processing, Team & Access, For Developers, Safekeeping & Health and Settings — everything to run the database, nothing it reasons over for you.

your-db.inventdb.cloud / admin
The Engine admin: Relationships, Data Quality, Search Freshness, Attachment Processing, Team and Access, For Developers, Safekeeping and Health, and Settings. No AI Budget, no Connections — AI-free.
The Engine — administer your own server: relationships, quality, search, access and health.

AI-free:no AI Budget and no Connections in this build — the data plane, with a clean way to run it.

Who it's for

For your AI agent — and the builders behind it. Not a business app.

Point the agent you already run — Claude Desktop, Hermes Agent, or OpenClaw — at a database it drives over MCP; or build straight against SQL and REST. A self-running database you own, not an AI that runs your business.

Builders

The DB behind AI-built apps

Spin up a database per app or per agent in seconds, then grow to production scale without a migration.

Engineers

A serious backend

A real SQL database with ACID guarantees, full consistency, search and vectors built in, behind a stable URL with a REST API.

Data teams

Your own encrypted volume

Single-tenant isolation enforced at the storage layer — your key, your volume, your process. Not a row in someone else's big table.

Scales up, too

A few thousand rows today. 250 million later.

Same database, same SQL, same API — from your first prototype to a quarter-billion records. No painful migration from a prototype database to a production one.

Segmented

Flat write throughput

Data is written in sealed, immutable segments with per-segment indexes — so writes stay fast as the database grows.

Pruned

Skips what it can

Bloom filters and zone-maps prune whole segments before reading, so a query over 250M rows touches a tiny fraction.

Columnar

Fast analytics at scale

Aggregations and GROUP BY run over compact columnar files, not row scans — dashboards stay fast at scale.

Built for production

Everything you expect from a database. And more, built in.

InventDB Serverless prices, but a genuinely serious database underneath — with search, vectors and files you'd normally bolt on as three more services.

SQL

Full SQL

Real SELECTs with joins, filters, GROUP BY and aggregates — the query language you already know.

ACID

Crash-safe writes

Multi-record writes are all-or-nothing. WAL-backed and crash-safe, with self-healing corruption recovery.

Consistent

Read your own writes

Fully consistent — no eventual-consistency window to design around.

Search

Four ways to search

Exact, fuzzy (typos), full-text and semantic-by-meaning — all from one query layer.

Vectors

Vectors built in

On-device embeddings and per-segment vector indexes. Build similarity search with no extra service.

Files

Files with OCR

Store PDFs and images alongside records; the text inside is extracted and indexed for search.

Encrypted

Your own key

AES-256-GCM at rest with a per-database key you rotate or revoke. Every key access audited.

Flexible

Schema without migrations

Add fields without downtime. The schema evolves transactionally as your app does.

MCP

MCP server built in

Every database ships a 51-tool MCP server — so any AI client can read and write it. No AI to host yourself.

MCP-native

One line to connect. Bounded by design.

Adding your database to Claude Desktop or any MCP client is a single line (right). From there, the 51 tools run bounded by the connecting credential's role and row rules — searching, safely writing (with review and audit), reading documents, running reports — with every call logged. The same guardrails apply to every agent, automatically, because row-level security and audit live in the database, not the agent. There's no chatbot in the box; that's InventDB SOAR's job.

InventDB Serverless is the data plane. The intelligence lives in someone else's agent — which connects over MCP and works your data through these tools. The database itself never reasons over your data. An agent never elevates past the connecting user.
RecordsSearch FilesSchema ReportsQuality AdminSQL
claude_desktop_config.json
// add your database as an MCP server
{
  "mcpServers": {
    "mydb": {
      "url": "https://<your-db>.inventdb.cloud/mcp",
      "auth": { "type": "oauth2" }
    }
  }
}
▸ connected · 51 tools · bounded by your role
One instance, three interfaces

Connect however you build.

Just HTTP and SQL — send a query with a bearer token, get JSON back. Every interface runs bounded by the caller's role and row rules.

SQLReads run straight at the database — the same endpoint SQL Studio uses.
RESTEvery capability a documented endpoint, with OpenAPI 3.1.
MCP51 tools so external AI agents drive your data — never elevating.
POST/sql — run reads against the database
GET/api/openapi.json — the full REST surface
isolation model
Shared-table serverless (others):
customers ▸ [ you · acme · globex · … ]
           one big table, row filters

InventDB Serverless:
you   ▸ /vol/you · own encrypted volume
acme  ▸ /vol/acme · own encrypted volume
globex▸ /vol/globex · own encrypted volume
one writer per volume — enforced by storage
Your own private database

Not a row in someone else's big table.

Most cheap serverless databases pack everyone into one shared cluster and keep tenants apart with row filters. One bad filter, one bug, and your data is in someone else's query. We give every customer their own encrypted volume and their own database process.

  • Dedicated encrypted volume per customer — no shared data plane
  • One writer, guaranteed by the storage layer, not a config flag
  • No noisy neighbors — isolation you can explain to a security reviewer
Honest about what it is

A database. Nothing more, nothing less.

InventDB Serverless is the pure database — it never reasons over your data and never implies built-in AI. You pay for the database; the intelligence is yours to bring.

250M
records on a single instance — no re-architecting
1 key
your own AES-256 key — rotate or revoke any time
4-way
search — exact, fuzzy, full-text, semantic
0 AI
no AI in the box — external agents connect over MCP

Spin up a database in minutes.

Flat pricing from $11/mo, grows to 250M records on the same database. Bring your own AI over MCP, or build straight against SQL and REST.