MCP.Market

DB Gateway MCP server

by sijunkim·io.github.sijunkim/db-gateway·v1.0.4
No reviews yet

145+ tools across 8 databases: MySQL, PostgreSQL, Redshift, MongoDB, Redis, Kafka, and more

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars32 downloads/wk

Reviews

Write one

Nobody has reviewed DB Gateway yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

DB Gateway tools (100, 29 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • dynamodb_batch_get_item

    Get multiple items from one or more DynamoDB tables in a single request

  • dynamodb_batch_write_itemwrite action

    Put or delete multiple items in one or more DynamoDB tables

  • dynamodb_create_tablewrite action

    Create a new DynamoDB table

  • dynamodb_delete_itemwrite action

    Delete an item from a DynamoDB table

  • dynamodb_delete_tablewrite action

    Delete a DynamoDB table (WARNING: This permanently removes the table and all its data)

  • dynamodb_describe_table

    Get detailed information about a DynamoDB table

  • dynamodb_get_item

    Get an item from a DynamoDB table by its primary key

  • dynamodb_list_tables

    List all tables in DynamoDB

  • dynamodb_put_itemwrite action

    Create or replace an item in a DynamoDB table

  • dynamodb_query

    Query items from a DynamoDB table using key conditions

  • dynamodb_scan

    Scan all items in a DynamoDB table (use with caution on large tables)

  • dynamodb_transact_write_itemswrite action

    Perform multiple Put, Update, Delete, or ConditionCheck operations atomically across one or more tables

  • dynamodb_update_itemwrite action

    Update an existing item in a DynamoDB table

  • elasticsearch_aggregate

    Perform aggregations on documents

  • elasticsearch_bulk

    Perform bulk operations (index, update, delete) in a single request

  • elasticsearch_count

    Count documents matching a query

  • elasticsearch_create_aliaswrite action

    Create an alias for an index

  • elasticsearch_create_indexwrite action

    Create a new index with optional settings and mappings

  • elasticsearch_delete_aliaswrite action

    Delete an alias from an index

  • elasticsearch_delete_documentwrite action

    Delete a document by ID

  • elasticsearch_delete_indexwrite action

    Delete an index (WARNING: This permanently removes the index and all its data)

  • elasticsearch_get_cluster_health

    Get the health status of the ElasticSearch/OpenSearch cluster

  • elasticsearch_get_cluster_info

    Get basic information about the ElasticSearch/OpenSearch cluster

  • elasticsearch_get_document

    Get a document by its ID

  • elasticsearch_get_index

    Get detailed information about a specific index

  • elasticsearch_get_index_settings

    Get the settings of an index

  • elasticsearch_get_mapping

    Get the mapping definition of an index

  • elasticsearch_index_document

    Index (create or update) a document

  • elasticsearch_list_aliases

    List all index aliases

  • elasticsearch_list_indices

    List all indices in the ElasticSearch/OpenSearch cluster

  • elasticsearch_refresh_index

    Refresh an index to make recent changes searchable

  • elasticsearch_search

    Search for documents using Query DSL

  • elasticsearch_update_documentwrite action

    Partially update an existing document

  • kafka_add_partitions

    Increase the number of partitions for a topic (cannot decrease partitions)

  • kafka_alter_topic_config

    Modify configuration settings for a Kafka topic

  • kafka_create_topicwrite action

    Create a new Kafka topic with specified partitions and replication factor

  • kafka_delete_consumer_groupwrite action

    Delete a consumer group. Group must be inactive (no running consumers)

  • kafka_delete_topicwrite action

    Delete a Kafka topic (WARNING: This permanently removes the topic and all its data)

  • kafka_describe_consumer_group

    Get detailed information about a consumer group including members and their assignments

  • kafka_describe_topic

    Get detailed information about a Kafka topic including partitions, leaders, and replicas

  • kafka_get_cluster_info

    Get Kafka cluster information including brokers, controller, and cluster ID

  • kafka_get_consumer_group_offsets

    Get committed offsets for a consumer group on a specific topic

  • kafka_get_latest_messages

    Get the most recent messages from a topic across all partitions

  • kafka_get_messages

    Read messages from a specific partition starting from a given offset

  • kafka_get_topic_config

    Get configuration settings for a Kafka topic (retention, cleanup policy, etc.)

  • kafka_get_topic_offsets

    Get offset information for each partition of a topic (current, high, low watermarks)

  • kafka_list_consumer_groups

    List all consumer groups in the Kafka cluster

  • kafka_list_topics

    List all topics in the Kafka cluster (excludes internal topics starting with __)

  • kafka_produce_message

    Produce a message to a Kafka topic (for testing purposes)

  • kafka_reset_consumer_offsets

    Reset consumer group offsets for reprocessing messages. Group must be inactive (no running consumers)

  • kafka_search_messages_by_content

    Search for messages by content (value contains search text). Scans from beginning of topic

  • kafka_search_messages_by_key

    Search for messages by key (exact match or contains). Scans from beginning of topic

  • kafka_search_messages_by_timestamp

    Search for messages within a specific time range

  • mongodb_aggregate

    Perform an aggregation pipeline on a MongoDB collection

  • mongodb_collection_stats

    Get statistics about a MongoDB collection (size, count, indexes, storage)

  • mongodb_count

    Count documents in a MongoDB collection matching an optional filter

  • mongodb_create_indexwrite action

    Create an index on a specified MongoDB collection

  • mongodb_delete_manywrite action

    Delete multiple documents from a MongoDB collection

  • mongodb_delete_onewrite action

    Delete a single document from a MongoDB collection

  • mongodb_distinct

    Get distinct values for a field in a MongoDB collection

  • mongodb_drop_collectionwrite action

    Drop a collection from a specified MongoDB database

  • mongodb_find_many

    Find multiple documents in a MongoDB collection

  • mongodb_find_one

    Find a single document in a MongoDB collection

  • mongodb_insert_manywrite action

    Insert multiple documents into a MongoDB collection

  • mongodb_insert_onewrite action

    Insert a single document into a MongoDB collection

  • mongodb_list_collections

    List all collections in a specified MongoDB database

  • mongodb_list_databases

    List all databases in MongoDB

  • mongodb_list_indexes

    List all indexes on a MongoDB collection

  • mongodb_update_manywrite action

    Update multiple documents in a MongoDB collection

  • mongodb_update_onewrite action

    Update a single document in a MongoDB collection

  • mysql_describe_table

    Describe the structure of a MySQL table

  • mysql_execute_batchwrite action

    Execute multiple SQL queries sequentially on a single connection. Useful for running several queries at once. All queries share the same connection, so SET variables and temporary tables persist across queries. Returns an array of { query, result } pairs.

  • mysql_execute_querywrite action

    Execute SQL query on MySQL database

  • mysql_explain_query

    Get the execution plan for a SQL query (EXPLAIN)

  • mysql_get_all_schemas

    Get CREATE TABLE statements for all tables in the current database

  • mysql_get_schema

    Get the CREATE TABLE statement for a specific MySQL table

  • mysql_get_table_relationships

    Get all foreign key relationships between tables in the current database

  • mysql_kill_processwrite action

    Kill a MySQL connection/query by process ID

  • mysql_list_connections

    List all configured MySQL connections with their status (connected/disconnected)

  • mysql_list_databases

    List all databases the current user can see in MySQL

  • mysql_list_indexes

    List all indexes on a specific MySQL table

  • mysql_show_processlist

    Show all running queries and connections in MySQL (SHOW FULL PROCESSLIST)

  • mysql_show_status

    Show MySQL server status variables (connections, queries, etc.)

  • mysql_show_tables

    Show all tables in the current MySQL database

  • mysql_show_variables

    Show MySQL server configuration variables

  • mysql_table_stats

    Get table statistics including row count, data size, and index size

  • mysql_use_database

    Switch to a different MySQL database

  • postgresql_describe_table

    Describe the structure of a PostgreSQL table

  • postgresql_execute_querywrite action

    Execute SQL query on PostgreSQL database

  • postgresql_explain_query

    Get the execution plan for a SQL query (EXPLAIN FORMAT JSON)

  • postgresql_get_schema

    Get the schema information for a specific PostgreSQL table

  • postgresql_kill_processwrite action

    Terminate a PostgreSQL connection/query by PID (pg_terminate_backend)

  • postgresql_list_databases

    List all databases the current user can see in PostgreSQL

  • postgresql_list_indexes

    List all indexes on a specific PostgreSQL table

  • postgresql_show_processlist

    Show all active queries and connections in PostgreSQL (pg_stat_activity)

  • postgresql_show_status

    Show PostgreSQL database statistics (connections, transactions, cache hits)

  • postgresql_show_tables

    Show all tables in the current PostgreSQL database (public schema)

  • postgresql_show_variables

    Show PostgreSQL server configuration variables (pg_settings)

  • postgresql_table_stats

    Get table statistics including row count, size, and vacuum info

  • postgresql_use_database

    Switch to a different PostgreSQL database (reconnects)

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

no findings
  • Code scan49 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 45 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How DB Gateway compares

Against every graded Databases MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 47% of 802 Databases servers
Tools
100
the typical Databases server has 8
Tools that change things
29%
typical: 10%. Fewer write tools means less an agent can break
Downloads a week
32
more than 19% of 324 Databases servers with a package

What its tools let an agent do: 60 read · 27 change · 13 send or post

Install DB Gateway in Claude Code, Cursor or VS Code

Runs npx -y db-gateway on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add db-gateway -- npx -y db-gateway
Add to Cursor

What the publisher says

From the DB Gateway repository's README, as published. We do not edit it. Read it on GitHub

DB Gateway MCP Server

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:

You: "Find users who signed up last month and never placed an order"

  1. mysql_get_all_schemas          → reads every table definition
  2. mysql_get_table_relationships  → finds the users ↔ orders foreign key
  3. mysql_execute_query            → runs the LEFT JOIN

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, mysqlexecutequery, and never sees a host, port, or password: those stay in the client config, and the agent only ever names the alias.

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:

{
  "mcpServers": {
    "db-gateway": {
      "command": "npx",
      "args": ["-y", "db-gateway"],
      "env": {
        "DBS": "mysql,redis",
        "MYSQL": "mysql://<user>:<password>@<host>:3306/<database>?alias=dev&default=true",
        "REDIS": "redis://:@<host>:6379/0?alias=dev&default=true"
      }
    }
  }
}

DBS decides which engines are enabled — only those tools get registered.

Connection strings

One string per engine. Semicolons separate multiple instances.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

DB Gateway: common questions

Is DB Gateway MCP server safe?
Mostly: it is graded B (78/100). Read the DB Gateway safety report
How do I install DB Gateway?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does DB Gateway need an API key?
Yes. The registry entry asks for MYSQL, POSTGRESQL, REDSHIFT, MONGODB and 5 more.
Is DB Gateway maintained?
The last commit was 85 days ago (2026-08-09). The latest release is v1.0.4.
What can I use instead of DB Gateway?
Servers from other publishers that do the same job: DBHub MCP server, Faucet MCP server and Quarry MCP server.
How does DB Gateway compare with other Databases MCP servers?
safety score 78/100 (higher than 47% of 802 Databases servers); tools 100 (the typical Databases server has 8); tools that change things 29% (typical: 10%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to DB Gateway

Same job from other publishers: the closest match first, then the best rated.

  • DBHub
    Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, SQLite
    A
  • Faucet
    SQL database to MCP tools and REST API: PostgreSQL, MySQL, SQL Server, Oracle, SQLite, Snowflake.
    A
  • Quarry
    Safety-railed database access: Postgres, MySQL, SQLite, Redis. Read-only by default.
    A
  • Appwrite
    Build and deploy backends: auth, Postgres/MySQL/vector databases, storage, functions, hosting, CDN
    A
  • Kubeshark
    Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
    A