db-mcp-server MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Multi-DB in one server — switch without restarting
Per-connection auto-generated tools (e.g. query_prod, schema_analytics)
TimescaleDB-native tools for time-series ops
Oracle: 10g-23c, RAC, Cloud Wallet

라이브 데모

실제 사용 모습

db.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "db": {
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "db",
      "command": "TODO",
      "args": [
        "See README: https://github.com/FreePeak/db-mcp-server"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "db": {
      "command": {
        "path": "TODO",
        "args": [
          "See README: https://github.com/FreePeak/db-mcp-server"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add db -- TODO 'See README: https://github.com/FreePeak/db-mcp-server'

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: db-mcp-server

Run cross-database analysis from Claude

👤 Data engineers ⏱ ~25 min intermediate

언제 쓸까: You need to pull from Postgres (app) AND MySQL (legacy) in one conversation without switching tools.

사전 조건

config.json with both connections — Repo docs show the shape; store credentials in env refs, not inline

흐름

Start the server

Run ./bin/server -t sse -c config.json and confirm both connections come up.✓ 복사됨

→ Server logs 2 connections ok
Query each

From prod (Postgres): users signed up last week. From legacy (MySQL): orders attributed to them. Join in memory.✓ 복사됨

→ Combined dataset

결과: Cross-system insights without a data warehouse.

함정

Read-only assumption breaks — agent runs INSERTs — Use DB-level read-only users per connection; don't rely on agent discipline

함께 쓰기: google-sheets

Manage TimescaleDB hypertables from Claude

👤 Observability / IoT teams ⏱ ~20 min advanced

언제 쓸까: You want to create/inspect hypertables and continuous aggregates without memorizing Timescale DDL.

흐름

Inspect existing hypertables

List all hypertables in metrics DB with chunk interval and row count.✓ 복사됨

→ Table of hypertables
Create a continuous aggregate

Create a 1-hour rollup on sensor_readings grouping by device_id, avg + max + min.✓ 복사됨

→ CAgg created; refresh policy configured

결과: Timescale ops in minutes, not Google searches.

Explain an unfamiliar schema to get onboarded fast

👤 Engineers inheriting a database ⏱ ~30 min beginner

언제 쓸까: Day 1 at a new team; you need a map of the DB.

흐름

Dump schema

Use schema_<conn_id> on prod. Return tables, FK graph, and row-count order.✓ 복사됨

→ Schema + FK map
Generate a glossary

For each table, infer a 1-line description from column names and sample rows (limit 5 per table).✓ 복사됨

→ Onboarding cheat sheet

결과: Working mental model in 30 min.

조합

다른 MCP와 조합해 10배 효율

db + google-sheets

Export a query result into a shared Sheet for non-tech stakeholders

Query top 50 customers by LTV from prod; write to the 'Top LTV' sheet.✓ 복사됨

db + prometheus

Cross-check DB slow-query findings with DB-level Prometheus metrics

For the slow query found via performance_prod, show the pg_stat_statements metrics from Prometheus for the same window.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
query_<db_id>	sql: str (SELECT)	Read data	1 query
execute_<db_id>	sql: str (DDL/DML)	Writes — guarded by DB permissions	1 query
transaction_<db_id>	statements: str[]	Multi-statement atomic changes	1 tx
schema_<db_id>	table?: str	Discovery / onboarding	metadata query
generate_schema_<db_id>	format: sql\|json	Export for docs/version control	metadata queries
performance_<db_id>	sql?: str	Tune a slow query	plan + stats

비용 및 제한

운영 비용

API 쿼터: Your DBs' capacity
호출당 토큰: Large result sets burn tokens fast — LIMIT aggressively
금액: Free MCP; DB hosting costs are yours
팁: Always add LIMIT / cap output; stream to a file via filesystem MCP for bigger pulls

보안

권한, 시크릿, 파급범위

최소 스코프: DB-level read-only user recommended for exploration

자격 증명 저장: config.json references env vars; never commit with inline passwords

데이터 외부 송신: Only to configured DB hosts

절대 부여 금지: DB superuser to the MCP connection unless absolutely needed

문제 해결

자주 발생하는 오류와 해결

Connection pool exhausted

Tune pool size in config.json; kill zombie sessions on DB side; verify no runaway agent loops

확인: SELECT * FROM pg_stat_activity (for Postgres)

Oracle wallet auth fails

TNS_ADMIN path must be readable by the MCP process; on mac/linux watch for SELinux/AppArmor

Tool names don't appear for one DB

That connection likely failed to init; check server logs — usually wrong creds or firewall

대안

db-mcp-server 다른 것과 비교

대안	언제 쓰나	단점/장점
postgres-mcp (official)	You only need Postgres	Single-DB
mysql-mcp (community)	You only need MySQL	Single-DB

db-mcp-server