数据库管理工具

> "Connect to my local PostgreSQL on port 5432, database myapp, user admin"

> "Create a group called backend and add this directory"

> "Connect to my PostgreSQL on localhost, put it in the backend group"

> "Set local-pg as the default connection"

> "Show me all tables"

> "What columns does the users table have?"

> "Show me the last 10 orders with the customer name"
  -> AI reads FKs from schema, builds the JOIN, applies LIMIT 10

> "Insert a test user called Alice"
  -> Snapshot captured for rollback

> "Oops, undo that"
  -> Rows restored via reverse SQL

> "Switch to the production database for this session"
  -> Instant context change, all queries now go to prod

> "Delete all inactive users"
  -> "This will affect N rows. Call again with confirm=true to proceed."

> "What did I run today?"
  -> Full query history with timestamps and execution times

> "Dump the database — structure and data"
  -> SQL file generated, ready for restore

"Create a group called backend"
"Add this directory as scope"
"Create a PostgreSQL connection called local-dev in the backend group"   <- auto-default (first connection)
"Create another called production in backend"
"List connections"                                                       <- shows local-dev (active, default)
"Switch to production"                                                   <- session only
"Set production as default"                                              <- persists between sessions

claude mcp add --scope user database -- npx -y @cocaxcode/database-mcp@latest

{
  "mcpServers": {
    "database": {
      "command": "npx",
      "args": ["-y", "@cocaxcode/database-mcp@latest"]
    }
  }
}

npm install -g postgres       # PostgreSQL (postgres.js)
npm install -g mysql2         # MySQL
npm install -g sql.js         # SQLite (runs in-process, no native bindings)

"Create a group called my-project and add this directory as scope"
"Create a connection called dev with host localhost, database myapp, user admin in my-project"
"Create a read-only connection called analytics pointing to ./data/metrics.db in my-project"
"Switch to dev"               -> queries go to PostgreSQL
"Switch to analytics"         -> queries go to SQLite
"Duplicate dev as dev-readonly with read-only mode"

"Create a group called frontend with scope /home/user/frontend"
"Create a group called backend with scope /home/user/backend"

"Show me available rollbacks"
"Rollback the last delete"
  -> "This will INSERT 47 rows back into orders. Confirm?"
  -> Rows restored via reverse SQL

"List all tables"                         -> names only (fast)
"Show me the users table with columns"    -> columns + types + nullable
"Full schema for orders including FKs"    -> columns + foreign keys + indexes
"Tables starting with user"              -> pattern: 'user%'

"Show me all users"
  -> SELECT * FROM users LIMIT 100         <- auto LIMIT

"Show the execution plan for this query"
  -> EXPLAIN ANALYZE with dialect-specific syntax (PostgreSQL/MySQL/SQLite)

// Example: normal (default) response
{
  "call_id": "k3m9a2xp",
  "columns": ["id", "title", "content"],
  "rows": [
    { "id": 1, "title": "Hello", "content": "<h1>Long HTML…(+1847B)" }
  ],
  "rowCount": 1,
  "executionTimeMs": 12,
  "cells_truncated": 1,
  "hint": "1 cell(s) truncated to 500 bytes. Use inspect_last_query({ call_id: \"k3m9a2xp\" }) for full values.",
  "tokens_saved_estimate": 462
}

"Dump the database"
  -> Choose: structure only or full
  -> Choose: all tables or specific ones
  -> SQL file saved to .database-mcp/dumps/

"Restore from the last dump"
  -> Lists available dumps, asks for confirmation, executes

"What queries did I run today?"
"Show me only mutations"
"History for the prod connection"

"Export all connections"                    -> JSON with masked passwords
"Export with secrets included"             -> JSON with real credentials
"Import these connections: { ... }"        -> creates missing connections

~/.database-mcp/                          # Global (configurable via DATABASE_MCP_DIR)
├── groups/                               # Connection groups with scopes and defaults
├── connections/                          # Connection configs (credentials, chmod 600)
├── project-conns.json                    # Session-only active connections (cleared on restart)
└── config.json                           # Server config (limits)

{your-project}/.database-mcp/            # Per-project (auto-gitignored)
├── history.json                          # Query history (max 5000)
├── rollbacks.json                        # Pre-mutation snapshots (max 1000)
└── dumps/
    └── {conn}-{timestamp}-{mode}.sql     # Database dumps

"Set max rollbacks to 2000"
"Set max history to 10000"

src/
├── index.ts              # Entry point (StdioServerTransport)
├── server.ts             # createServer() factory
├── tools/                # 33 tool handlers (one file per category)
├── resources/            # MCP Resources (schema auto-discovery)
├── services/             # Business logic
│   ├── connection-manager    # Lazy connect, driver caching
│   ├── schema-introspector   # Multi-dialect introspection (3 detail levels)
│   ├── query-executor        # Read/mutation/explain with safety
│   ├── rollback-manager      # Snapshot capture + reverse SQL
│   ├── history-logger        # Per-project query log
│   └── dump-manager          # Dump/restore (SQL generation)
├── drivers/              # Database adapters (postgres, mysql, sqlite)
├── lib/                  # Types, storage, sanitization
└── utils/                # SQL classifier, parser, formatter