dbhub

dbhub is a plugin for Claude Code from bytebase/dbhub. Its manifest loads nothing; the 2 skills, 1 MCP server it bundles cost 50 tokens per session together, scanned A, original, MIT.

A database service that lets an AI agent connect to PostgreSQL, MySQL, MariaDB, SQL Server, or SQLite and explore their schemas. A schema describes the tables, columns, and relationships in a database.

In plain words
What is it for?
Configuring a database connection with a DSN, then exploring tables and other schema details across the supported database systems.
Why use it?
It reduces the amount of database structure an agent must load or inspect manually. A read-only, least-privilege account can limit the connection's ability to change data.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Configuring a database connection with a DSN, then exploring tables and other schema details across the supported database systems.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add bytebase/dbhub
/plugin install dbhub
About the project

DBHub is a lightweight Model Context Protocol server that lets compatible AI clients connect to and explore PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite databases through one interface. Developers and other users employ it for schema inspection, query validation, debugging, and controlled read-only database access; the catalogue entries provide agent skills, instructions, an MCP configuration, and a plugin.

bytebase/dbhub · 3,664 stars · on GitHub · dbhub.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/bytebase/dbhub

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dbhub

README.md
[![agentmods](https://agentmods.dev/badge/plugins/bytebase/dbhub/plugin/github.svg)](https://agentmods.dev/plugins/bytebase/dbhub/plugin)
Your own site
<a href="https://agentmods.dev/plugins/bytebase/dbhub/plugin"><img src="https://agentmods.dev/badge/plugins/bytebase/dbhub/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dbhub

Your own site · 80×15
<a href="https://agentmods.dev/plugins/bytebase/dbhub/plugin"><img src="https://agentmods.dev/badge/plugins/bytebase/dbhub/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 2 skills, 1 MCP server cost 50 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

dbhub scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 32 lines

What it actually says

{
  "name": "dbhub",
  "description": "Token-efficient database MCP server for PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, and SQLite, with skills for connection setup and schema exploration",
  "version": "1.5.0",
  "author": {
    "name": "Bytebase",
    "url": "https://www.bytebase.com"
  },
  "homepage": "https://dbhub.ai",
  "repository": "https://github.com/bytebase/dbhub",
  "license": "MIT",
  "keywords": [
    "database",
    "sql",
    "postgres",
    "mysql",
    "mariadb",
    "sqlserver",
    "oracle",
    "sqlite"
  ],
  "userConfig": {
    "dsn": {
      "type": "string",
      "title": "Database connection string (DSN)",
      "description": "Examples: postgres://user:password@localhost:5432/dbname | mysql://user:password@localhost:3306/dbname | mariadb://user:password@localhost:3306/dbname | sqlserver://user:password@localhost:1433/dbname | oracle://user:password@localhost:1521/FREEPDB1 | sqlite:///path/to/database.db. Append ?sslmode=require for SSL. Use a least-privilege, read-only database account.",
      "sensitive": true,
      "required": true
    }
  }
}
Contents

What it installs

The manifest is a name and a version. 2 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 50 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago Changed 0359e6161fa9
  2. 18d ago Changed e6d684dfdc3a
  3. 25d ago Changed 08033104ab0e
  4. 27d ago Changed · +1 lines eb078dbd3ef6
  5. 1mo ago Changed ae1f44bf50d6
  6. 1mo ago Changed 31998f3ef8dd
  7. 1mo ago Changed 5f40d07da3d6
  8. 1mo ago First seen · 31 lines scan A 5e6b0a80997c

Subscribe to this mod's changes

dbhub is a plugin published in the GitHub repository bytebase/dbhub (3,664 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.