DBLift ships an MCP (Model Context Protocol) server so an AI coding agent — Claude Code, Cursor, GitHub Copilot, Windsurf — can call DBLift's existing checks directly, in-process, instead of shelling out to the CLI or guessing at migration safety. Every tool returns the same JSON as the equivalent --format json command output. There is no LLM in the apply path: tools are deterministic checks, gated by the same licence tiers as the CLI commands they wrap. Destructive or write commands (clean, undo, a real migrate apply, data apply/undo) are never exposed as tools.
Install
pip install dblift
Configure your agent
Add DBLift as an MCP server. Most clients read a JSON config with a mcpServers block.
.mcp.json (Claude Code) or the equivalent config file for your client:
{
"mcpServers": {
"dblift": {
"command": "dblift",
"args": ["mcp"]
}
}
}
| Client | Config file |
|---|---|
| Claude Code | .mcp.json in the project root, or claude mcp add dblift -- dblift mcp |
| Cursor | .cursor/mcp.json |
| GitHub Copilot (VS Code) | .vscode/mcp.json |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
Tools by edition
Tool availability follows the same licence tiers as the CLI — see Editions and Tiers.
| Edition | Tools | Resource |
|---|---|---|
| OSS Core | info · validate · migrate_dry_run (forces --dry-run) | dblift://history |
| Pro | diff · validate_sql · export_schema · data_plan · data_status | — |
| Enterprise | plan · preflight · snapshot · diff_impact | — |
A tool from a tier your licence doesn't cover behaves like the equivalent CLI command on the open-source build: it reports what it does and exits without running, rather than failing silently.
What an agent can ask
With the server configured, an agent can, for example:
- Check migration status and pending migrations (
info) - Validate migration history consistency (
validate) - Preview a migration without applying it (
migrate_dry_run) - Diff live schema against migrations, or validate a SQL script against your rule profile (Pro)
- Run a full preflight check or generate an evidence snapshot before a release (Enterprise)
None of this replaces review — it gives the agent the same ground truth a human reviewer would use, instead of it inferring migration safety from reading SQL files.
See Commands for what each underlying command does.