CSV and Google Sheets MCP server and REST API for AI agents
Open-source Agent OS for TypeScript that helps teams operate AI agents like production systems
Stage
Not given
Not given
Founded
Not given
Not given
Based in
NL
Not given
Pricing model
Not given
Open source
Pricing
Free: €0, 3 datasets, 100,000 rows per dataset, 1,000 queries per day, 2 people. Pro: €12/month or $12/month, 25 datasets, 2,000,000 rows per dataset, 50,000 queries per day, 5 people per workspace. Business: Custom pricing.
Not given
Key features
Automatic dataset linking by shared IDs and codes
Supports MCP protocol for Claude, ChatGPT, and Cursor
REST API for apps and automations
Automatic version tracking on data changes
Team collaboration with role-based access
Messy file import with validation reports
EU data hosting with no AI provider access
Activity logs showing data changes and queries
Durable execution with crash-safe HITL
Agent DNA for versioning agents as packages
Gatekeeper default-deny authorization
Skillgate capability curation
Local-first deployment without Kubernetes requirement
Agent VM with effect typing and speculation
Decision Runtime for bounded closed-set judgment
Organism for multi-agent coordination
What makes it different
Query results use 475 times fewer tokens than pasting entire sheets
Exact totals computed by database instead of estimated by AI
Read-only by design prevents agents from modifying data
Hosted in EU with automatic backups and 14-day retention
One MCP URL works across multiple AI agent platforms
Agents live in the same TypeScript DI app as your APIs, not as separate services
Production-ready without cloud or Kubernetes dependency
Complete operating system, not glue between frameworks
Agents pause, resume, and survive restarts in production
Developer-first with decorators and DI patterns developers already know
datatomcp
HazelJS