S1 · HERO
v2.0 now available · 34 MCP tools
⬡ npm · datavor v2.0

The AI-Native Database
Sync & Pipeline MCP

Sync, transform, schedule, and monitor your data pipelines across MySQL, PostgreSQL, SQL Server, SQLite, and Snowflake using natural language through Claude or AI agents.

No SQL. No complex UIs. No data engineers. Just ask.

$ npm install -g datavor ⧉ copy
Read the Docs →
Free forever for Phase 1 Works with Claude Desktop 5-minute setup
Claude Desktop · Datavor
You
Sync my customers table from MySQL to PostgreSQL
Claude · Datavor
✅ Connected to MySQL — 10,542 rows found
✅ Connected to PostgreSQL
⟳ Syncing in batches of 100...
✅ Done — 10,542 customers synced in 5.2s
You
Now sync only USA customers incrementally
Claude · Datavor
⚡ Incremental mode — checking updated_at...
✅ Synced 47 changed rows in 0.3s
Live sync status
🐬
MySQL
✓ customers
✓ orders
✓ products
⟶
syncing
🐘
PostgreSQL
✓ customers
✓ orders
· products
10,542 rows · 5.2s · 0 errors
Ready to use with Claude Desktop, Claude Code, and any MCP client ⬇ Download on npm
S2 · HOW IT WORKS
How it works

Three steps.
Seconds, not hours.

1
🔌

Install & Connect

Add Datavor to Claude Desktop with one config block. Works on macOS in minutes.

~5 min setup
2
💬

Ask Claude

Tell Claude what you need in plain English. No SQL required — Datavor handles the rest.

natural language
3
✅

Done

Datavor executes precise operations, handles errors, and gives you a full sync report.

instant results
claude_desktop_config.json — the complete setup
{
  "mcpServers": {
    "datavor": {
      "command": "datavor"
    }
  }
}
One config block. Restart Claude. Done.
S3 · FEATURES
What Datavor can do

Everything your databases need.
Nothing you don't.

Visual Schema Tools

See differences before you sync.

Ask Claude to compare any table between your MySQL and PostgreSQL databases. Get a clean visual diff showing missing columns, type mismatches, and index differences — all before a single row is touched.

  • Side-by-side column comparison
  • Type mismatch highlighting
  • Complete migration analysis across all tables
  • AI-powered recommendations on what to fix first
Schema comparison · customers table
🐬 MySQL
🐘 PostgreSQL
idINT
idINTEGER
nameVARCHAR(100)
nameVARCHAR(100)
emailVARCHAR(100)
emailmissing
created_atDATETIME
created_atTIMESTAMP
countryVARCHAR(50)
countryVARCHAR(50)
⚠ 2 differences found — sync may need type conversion
Incremental Sync

Stop re-syncing everything, every time.

After your first full sync, Datavor remembers the checkpoint. Every subsequent sync fetches only new and changed rows — making daily updates 50–98% faster as your tables grow.

  • Timestamp-based change detection
  • Automatic checkpoint tracking
  • Works with any table that has an updated_at column
  • Falls back to full sync gracefully
Incremental sync performance
SYNCING 10,000 ROWS — CUSTOMERS TABLE
Full sync (first run)
15.0s
all 10,000 rows
Incremental (next day)
0.3s
47 changed rows only
98%
faster than full sync
after first run
⭐ New in v2.0 — Multi-Connector

Five databases. One tool. Any direction.

Datavor v2.0 connects to MySQL, PostgreSQL, SQL Server, SQLite, and Snowflake — and syncs between any combination. One natural-language request, any source to any target.

  • All 5 engines fully supported — read, write, sync, transform
  • Universal type engine with O(n) complexity — no per-pair mappings
  • Cross-engine migrations: MySQL → Snowflake, SQLite → PostgreSQL and more
  • 34 MCP tools across all connectors
Also compatible with cloud databases
Aiven
PlanetScale
☁AWS RDS
Azure SQL
Supabase
Supported databases — v2.0
Sync between any combination
MySQL
v1.0+
PostgreSQL
v1.0+
SQL Server
v2.0 ⭐
SQLite
v2.0 ⭐
Snowflake
v2.0 ⭐
"Sync orders from MySQL to Snowflake daily"
✅ Connected MySQL · Snowflake
✅ DATETIME→TIMESTAMP_NTZ, JSON→VARIANT
✅ 45,231 rows synced in 18.2s
⭐ New in v2.0 — Context Engine

Datavor learns your data over time.

The Context Engine builds a persistent local knowledge brain that silently learns from every interaction — schema changes, business rules, sync patterns, and table relationships.

  • Remembers your schema and detects changes automatically
  • Learns business rules from sync patterns — auto-applies them
  • Tracks foreign key relationships across databases
  • Ask "What do you know about the orders table?" and get a full briefing
Context Engine — explain database
"Explain my production MySQL database"

📖 production_db (MySQL)
Tables: 23 known
Rules: 4 active (2 auto-applied)
Syncs: 142 recorded · 97.2% success
Rows moved: 890,000 total
Changes: 2 schema changes detected
Since: 2026-01-15

💡 Auto-rule: exclude_test_orders
email NOT LIKE '%@test.com%' · used 47×
⭐ New in v1.5 — Scheduler

Set it and forget it.

Create automated sync jobs using plain English schedules. Datavor runs them on time — no Claude Desktop required, no cron expertise needed.

  • "Every night at 2am" → 0 2 * * * auto-generated
  • List, pause, resume, or trigger jobs instantly
  • Run 24/7 via daemon — fully independent of Claude
  • 6 new scheduler tools
Scheduler — active jobs
📅 Sync Jobs (3 active)
▶ Nightly orders sync
orders · Daily at 02:00 · Last run: ✅ Success · 14 runs
▶ Hourly inventory check
inventory · Every hour · Last run: ✅ Success · 312 runs
⏸ Weekly customer export
customers · Weekly Sun 02:00 · Paused
⭐ New in v1.5 — Transforms

Shape your data during sync.

Rename columns, convert types, filter rows, remap values — all inline during sync. Zero extra passes, zero temp tables. Preview on real data before committing a single row.

  • 5 transform types: rename, cast, filter, computed, value_map
  • Live before/after preview on sample rows
  • Transforms applied inline — no post-processing step
  • Perfect for schema mismatches and legacy migrations
Transform preview · customers
Before
customer_id │ score │ country
1           │ 95.5 │ US
2           │ 72.0 │ UK
After
cust_id │ score │ country
1       │ 95.5 │ United States
2       │ 72.0 │ United Kingdom
✓ Renamed: customer_id → cust_id  ·  ✓ Remapped: country codes
⭐ New in v1.5 — Dashboard

Know what's running, what failed, and why.

Every sync is automatically recorded to a local ledger. Ask Claude for a dashboard summary any time — success rates, rows moved, failure diagnostics, and table-level history.

  • Overall health: success rate, rows moved, daily trend
  • Per-table run history with incremental cursors
  • Failure log with specific fix suggestions
  • Reads from local file — instant, no database needed
Dashboard summary · last 7 days
98%
Success rate
126k
Rows moved
21
Runs completed
1
Failures
Most active tables
orders             45,231 rows · 7 runs
customers         10,542 rows · 7 runs
inventory          70,227 rows · 7 runs
Database Explorer

Browse your database like a pro.

Before you sync anything, ask Claude to show you a tree view of your database. See all tables, row counts, and column structures at a glance — perfect for large databases with 50+ tables.

  • Hierarchical tree view of all tables
  • Live row counts per table
  • Column types and constraints inline
  • Works on both MySQL and PostgreSQL
Database tree view · production_db
📁production_dbMySQL
🗃️customers10,542 rows
·idINT · PK
·emailVARCHAR(100) · UNIQUE
·countryVARCHAR(50)
🗃️orders45,231 rows
·idINT · PK
·customer_idINT · FK
·created_atDATETIME
🗃️products523 rows
🗃️categories48 rows
S4 · STATS
By the numbers

Fast. Free.
Built to scale.

5s
Sync 10,000 rows
98%
Faster with incremental sync
$0
Phase 1, forever free
34
MCP tools available
S5 · ECOSYSTEM
Built for the AI ecosystem

Works wherever
Claude works.

Datavor is an MCP server — the open standard for connecting AI agents to the tools they need. If it runs Claude, it runs Datavor.

👤 You
natural language
— choose your client —
Claude Desktop
direct · recommended
Claude Code
direct · CLI
Any MCP Client
Cline, Cursor & more
▼
▼
▼
Datavor MCP
this tool
▼
▼
🐬MySQL
source or target
🐘PostgreSQL
source or target
🔮
S6 · USE CASES
Who it's for

Built for everyone
who works with data.

🚀 Migration

Migrating from MySQL to PostgreSQL?

Analyze schema differences, get an AI-recommended sync order, and move your data in minutes — not months.

Hours → Minutes
🧪 Development

Copy production data to your dev environment

Populate your local database with real data for testing. Filter to only the rows you need — zero risk to production.

Safe · Fast · Filtered
📊 Analytics

Feed your analytics database automatically

Sync sales, customer, or event data from your operational DB to your analytics DB — incrementally, daily.

Incremental · Daily · Free
🛡️ Backups

Lightweight, intelligent database backups

Initial full sync, then daily incremental updates. Keep a live replica database without the cost of enterprise tools.

99% faster than full daily backup
Explore Datavor

v1.0 to v2.0 —
everything you get, free.

See the full breakdown of features across all versions — Multi-Connector, Context Engine, Scheduler, Transforms, Dashboard and more.

Explore All Features →
Free. No credit card. No time limit.
S8 · FAQ
FAQ

Common questions.

Do I need to know SQL?

No. Just describe what you want in plain English to Claude. Datavor translates your request into precise SQL operations automatically — no database expertise required.

What operating systems are supported?

Phase 1 supports macOS. Phase 2 will add full support for Windows and Linux, making Datavor available across all major platforms.

Is my data sent to any third party?

No. Datavor runs locally on your machine and connects directly to your databases. Your data never passes through Datavor's servers — it stays between you and your databases.

What databases are supported?

Phase 1 supports MySQL and PostgreSQL. Phase 2 will add MongoDB, SQLite, Supabase, AWS RDS, Google Cloud SQL, and more.

Does it work with remote databases?

Yes. Datavor connects to any accessible MySQL or PostgreSQL server — localhost, your office network, cloud-hosted (AWS RDS, DigitalOcean, etc.). Just provide the host, port, and credentials.

Can it sync bidirectionally?

Yes. MySQL → PostgreSQL and PostgreSQL → MySQL both work. You specify the source and target in each request, and Datavor handles the direction and data type conversions automatically.

What is MCP?

MCP (Model Context Protocol) is an open standard by Anthropic that lets AI agents like Claude connect to external tools and services. Datavor is an MCP server — meaning Claude can use it directly, like a skilled database assistant.

What happens if a sync fails mid-way?

Datavor syncs in batches and logs exactly which rows succeeded or failed. A partial failure won't corrupt your target database — each batch is atomic. You'll get a full report and can retry safely.

S9 · FINAL CTA

Your databases. Your AI.
Ready in 5 minutes.

Install Datavor, connect Claude Desktop, and sync your first table before you finish your coffee.

$ npm install -g datavor ⧉ copy
Read the Docs →
Free. Open to feedback. Built for the AI era.