
Db Gateway
io.github.sijunkimPublished by GitHub account sijunkimv1.0.4Updated Oct 25, 2026
145+ tools across 8 databases: MySQL, PostgreSQL, Redshift, MongoDB, Redis, Kafka, and more
Overview
A local MCP server that gives an AI assistant 145+ tools to inspect schemas and run queries across eight database and streaming engines from one config.
- What you can do
- Read schemas and table relationships, then run queries against MySQL, PostgreSQL and Redshift (relational engines). Work with documents, keys and caches in MongoDB, Redis and DynamoDB (NoSQL engines). Search and manage indices in Elasticsearch. Inspect and work with topics and messages in Kafka. Address multiple instances of one engine by alias, with a default instance when none is given.
- When to use it
- Useful when an assistant should explore a database itself instead of being fed DDL, or when a stack spans several engines (for example MySQL for the app, Redshift for analytics, Redis for cache, Kafka for events) and you want one server and one config block rather than several.
- Requirements
- Runs locally via npx and needs Node.js 18 or newer. DBS is required and lists the engines to enable. Each enabled engine needs its connection string variable (MYSQL, POSTGRESQL, REDSHIFT, MONGODB, REDIS, ELASTICSEARCH, KAFKA), each with a required alias; DynamoDB instead uses DYNAMODB_REGION, DYNAMODB_ACCESS_KEY_ID and DYNAMODB_SECRET_ACCESS_KEY. Network access to the target databases.
Installation
In SourceWeft
- Open Db Gateway in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
DB Gateway MCP Server
[npm] [MCP Registry] [8 databases] [license]
English | 한국어
An MCP server that gives AI agents direct access to your databases — 145+ tools across 8 engines.
The point is that the agent reads your schema itself instead of you pasting DDL into a prompt:
Why db-gateway?
Most database MCP servers cover one engine, or a handful of relational ones. If your stack is MySQL for the app, Redshift for analytics, Redis for cache, and Kafka for events, that means four servers with four different config styles.
This is one server, one config block:
DBS decides which of them are enabled — only those tools get registered, so a MySQL-only setup stays a MySQL-only tool list.
See It Work
Every screenshot below is one real session against a development MySQL database holding 249 rows — unedited output, not mock data. The agent calls a single tool, mysql_execute_query, and never sees a host, port, or password: those stay in the client config, and the agent only ever names the alias.
[Step 1 — READ: query the most recently added item]
[Step 2 — CREATE: insert a new item, and MySQL returns its insertId]
[Step 3 — UPDATE: move it to the freezer, matching exactly one row by primary key]
[Step 4 — DELETE: remove that row by primary key]
[Step 5 — VERIFY: the table is back to its original 249 rows]
Point the same server at production with READ_ONLY=true and steps 2 through 4 simply do not exist — the write tools are never registered, so the agent cannot see them to call them.
Quick Start
Requires Node.js 18+. Register it with your MCP client — no install step:
DBS decides which engines are enabled — only those tools get registered.
Connection strings
One string per engine. Semicolons separate multiple instances.
aliasis required. It is how tools address a specific instance — omit it and that engine fails to connect.
Several instances of the same engine — separate their connection strings with a semicolon. The agent picks one by passing an alias argument to any tool; default=true marks the one used when no alias is given:
DynamoDB is the exception — it takes DYNAMODB_REGION, DYNAMODB_ACCESS_KEY_ID, and DYNAMODB_SECRET_ACCESS_KEY instead. See .env.example for every option.
Read-Only Mode
READ_ONLY=true hides write tools from the tool list entirely and restricts *_execute_query to SELECT-style statements.
Register production as a second MCP server with this flag on. The agent then cannot modify production data — the write tools do not exist as far as it can see.
Documentation
- Tool Reference — all 145+ tools, by engine
- Connection Management — pooling, health checks, and why
connectionLimitmultiplies per session - Deployment — SSE mode, Nginx, PM2, sharing one gateway across a team
License
MIT
Source: README.md at commit 895c500
Tools
0Version history
1- v1.0.4LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts