db-mcp-server MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

Live Demo

What it looks like in practice

db.replay ▶ ready

0/0

Install

Pick your client

~/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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use db-mcp-server

Run cross-database analysis from Claude

👤 Data engineers ⏱ ~25 min intermediate

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

Prerequisites

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

Flow

Start the server

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

→ 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.✓ Copied

→ Combined dataset

Outcome: Cross-system insights without a data warehouse.

Pitfalls

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

Combine with: google-sheets

Manage TimescaleDB hypertables from Claude

👤 Observability / IoT teams ⏱ ~20 min advanced

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

Flow

Inspect existing hypertables

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

→ Table of hypertables
Create a continuous aggregate

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

→ CAgg created; refresh policy configured

Outcome: Timescale ops in minutes, not Google searches.

Explain an unfamiliar schema to get onboarded fast

👤 Engineers inheriting a database ⏱ ~30 min beginner

When to use: Day 1 at a new team; you need a map of the DB.

Flow

Dump schema

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

→ Schema + FK map
Generate a glossary

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

→ Onboarding cheat sheet

Outcome: Working mental model in 30 min.

Combinations

Pair with other MCPs for X10 leverage

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.✓ Copied

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.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

API quota: Your DBs' capacity
Tokens per call: Large result sets burn tokens fast — LIMIT aggressively
Monetary: Free MCP; DB hosting costs are yours
Tip: Always add LIMIT / cap output; stream to a file via filesystem MCP for bigger pulls

Security

Permissions, secrets, blast radius

Minimum scopes: DB-level read-only user recommended for exploration

Credential storage: config.json references env vars; never commit with inline passwords

Data egress: Only to configured DB hosts

Never grant: DB superuser to the MCP connection unless absolutely needed

Troubleshooting

Common errors and fixes

Connection pool exhausted

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

Verify: 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

Alternatives

db-mcp-server vs others

Alternative	When to use it instead	Tradeoff
postgres-mcp (official)	You only need Postgres	Single-DB
mysql-mcp (community)	You only need MySQL	Single-DB

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills