The Data-Bridge

Governed AI access to the data you already have — wherever it already is.

Self-hosted middleware that makes your existing databases queryable over REST, SQL, and MCP — without moving them into a cloud warehouse or routing them through a SaaS copilot. Every query is audited, and the audit log is yours.

AGPLv3 Docker Python 3.12+

What it does

Your existing data, wherever it lives

Connect the databases you already run — Postgres, MySQL, SQL Server, Snowflake, CSV — with no migration and no consolidating everything into one cloud warehouse.

One governed surface for AI

Query every source over REST, SQL, and MCP at once. Point Claude Desktop, Cursor, or any MCP client straight at it — read-only enforced, no custom integration.

An audit log you own

Every query, result, and AI tool call is logged to a tamper-evident audit log on your own infrastructure. You always know what was asked and what came back.

On your infrastructure, not a SaaS

Runs in one Docker command on your own infra. Your data never leaves your perimeter or routes through a SaaS copilot — and OAuth 2.1, RBAC, and rate limiting keep access governed.

Try it in 30 seconds

# Free Community Edition — CSV, no clone, no build
export TDB_API_KEYS=$(python3 -c "import secrets; print(secrets.token_hex(32))")

docker run --rm -p 8000:8000 \
  -e TDB_API_KEYS \
  -v "$PWD/data:/data:ro" \
  ghcr.io/tdb-project/tdb-community:latest

Then open http://localhost:8000/docs, register a CSV, and query it from REST or an AI tool. Full quickstart →

Community & Enterprise

Community

Free · AGPLv3 · self-hosted
  • CSV data source
  • REST + MCP API (query_source)
  • Read-only, 1,000-row cap
  • Local NDJSON audit log
  • One Docker command
View on GitHub