Drizzle Sentinel MCP
Enables database governance for Drizzle ORM projects by inspecting schemas, linting migrations for unsafe operations, detecting schema drift, and explaining query plans with performance checks.
README
š”ļø Drizzle Sentinel MCP
Production-Grade TypeScript MCP Server for Drizzle ORM Schema Inspection, Migration Safety Linting, and Schema Drift Detection.
š Overview & Purpose
Autonomous coding agents (Claude Code, Cursor, Codex) frequently hallucinate or generate unsafe database migrations ā such as adding NOT NULL columns without default values, dropping active columns, or forgetting indexes on foreign keys.
Drizzle Sentinel MCP is built for modern TypeScript engineering stacks (Turborepo + Drizzle ORM + Express / Next.js). It injects closed-loop database governance directly into agentic development workflows via the official Model Context Protocol.
šļø System Architecture
graph TD
Agent[Agentic IDE / Claude Code / Cursor] -->|MCP Protocol / stdio| Sentinel[š”ļø Drizzle Sentinel MCP Server]
subgraph Tools [MCP Governance Toolsuite]
Sentinel --> T1[š inspect_drizzle_schema]
Sentinel --> T2[šØ lint_drizzle_migration]
Sentinel --> T3[𩺠detect_schema_drift]
Sentinel --> T4[ā” explain_query_plan]
end
T1 --> Parser[Drizzle Schema AST Parser]
T2 --> Engine[Rules Engine: NO_DROP, DEFAULT_ON_NOT_NULL, UNINDEXED_FK]
T3 --> Drift[Drift Doctor & Safe Patch Generator]
T4 --> Sandbox[Read-Only Query Sandbox & Smell Detector]
Parser --> AppCode[TypeScript Drizzle Schemas]
Engine --> Migrations[Drizzle Migration .sql Files]
Drift --> Database[(PostgreSQL / SQLite / MySQL)]
š ļø MCP Tools Provided
inspect_drizzle_schema: Deeply analyzes TypeScript Drizzle schemas, mapping tables, relations, and identifying foreign keys lacking index coverage.lint_drizzle_migration: Evaluates SQL migration statements against production safety rules:NO_RAW_DROP_TABLE: Blocks destructive table drops.NO_RAW_DROP_COLUMN: Enforces expand-contract migrations.REQUIRE_DEFAULT_ON_NOT_NULL: Prevents migration failures & table locks on existing tables.NO_UNINDEXED_FOREIGN_KEYS: Warns on missing FK index coverage.
detect_schema_drift: Compares declared TypeScript schema with live database tables, pinpointing missing columns/tables and emitting non-breaking zero-downtime remediation SQL.explain_query_plan: Enforces a strict read-only execution sandbox and flags performance smells (MISSING_LIMIT,WILDCARD_PROJECTION,SORT_MEMORY_RISK).
š Repository Structure
drizzle-sentinel-mcp/
āāā packages/
ā āāā mcp-server/ # TypeScript MCP server implementation
ā ā āāā src/tools/ # Tool handlers (inspect, lint, drift, sandbox)
ā ā āāā src/services/ # AST & schema parsers
ā ā āāā src/index.ts # Stdio server entrypoint
ā āāā rules-engine/ # AST & regex defensive migration rules
āāā apps/
ā āāā demo-service/ # Express + Drizzle ORM reference application
āāā tests/ # Vitest comprehensive unit & integration test suite
āāā turbo.json # Turborepo task pipeline
āāā CLAUDE.md # Agentic guidelines & operating rules
āāā README.md
š Quickstart & Setup
1. Install Dependencies & Build
npm install
npm run build
2. Run Test Suite
npm test
3. Register with Claude Code / Cursor MCP Config
Add the server to your claude_desktop_config.json or .cursor/mcp.json:
{
"mcpServers": {
"drizzle-sentinel": {
"command": "node",
"args": ["<path-to-repo>/packages/mcp-server/dist/index.js"]
}
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.