// agents · bytebase/dbhub

dbhub

dbhub é um projeto de agentes de IA de código aberto de bytebase (bytebase/dbhub no GitHub). Tem 3.618 estrelas no GitHub e 316 forks, é publicado sob a licença MIT e foi atualizado pela última vez no GitHub em 2 de outubro de 2026.

A token-conscious MCP server that connects AI tools to Postgres, MySQL, SQLite and more.

★ 3,6 mil estrelas⑂ 316 forksMITatualizado out 2026

Ver no GitHub ↗Official site ↗

▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.

// dados do projeto

Dados do projeto

Repositório: bytebase/dbhub
Estrelas no GitHub: 3.618
Forks: 316
Licença: MIT
Última atualização no GitHub: 2 de outubro de 2026
Categoria: Agentes de IA
Tipo de ficha: Guia de instalação completo
Site oficial: Official site

// como funciona

Como funciona

Clarify your goal
Decide the first concrete outcome you want from it, so you can pick the right example, template or mode instead of exploring everything at once.
Get the project
Clone the repository (or install the published package) and skim its README quick start for the requirements for your platform.
Install and configure
Run the documented install step and set any required configuration — such as provider keys, data sources or local services — before the first run.
Run your first task
Execute the smallest documented example end to end, confirm the output is what you expected, then adapt it to your real data or workflow.

// recursos

Por que as pessoas gostam tanto

Multi-database, one server

PostgreSQL, MySQL, MariaDB, SQL Server, Oracle and SQLite through a single MCP interface — no separate server per database.

Minimal, token-efficient tools

execute_sql, search_objects and opt-in explain_sql / health_check keep context use small.

Custom tools

Define reusable, parameterised SQL operations in dbhub.toml for your team.

Guardrails

Read-only mode, row limiting and query timeouts prevent runaway operations against production.

Secure access

SSH tunneling and SSL/TLS encryption for reaching databases safely.

Workbench included

A web workbench for exploring and querying connected databases.

// execute você mesmo

Execute você mesmo

Clone the repository
Get the source so you can inspect, configure and run it locally.
```
git clone https://github.com/bytebase/dbhub.git
cd dbhub
```

Run DBHub with npx

Point it at a database with a DSN — no install required.

npx @bytebase/dbhub@latest --transport http --port 8080 --dsn "postgres://user:password@localhost:5432/dbname?sslmode=disable"

Add it to your MCP client
Register the same command (stdio transport) in your client's MCP config and restart the client, as the README shows.
```
npx @bytebase/dbhub@latest --transport stdio --dsn "postgres://user:password@localhost:5432/dbname"  # see README for client config
```

// casos de uso

O que você pode criar

Let Claude Code explore a local Postgres schema safely in read-only mode
Give non-technical staff curated, read-only database access via Claude Desktop
Consolidate five per-database MCP servers into one process
Troubleshoot production data with timeouts and row limits as guardrails

// perguntas frequentes

Perguntas frequentes

Who maintains dbhub?

It is maintained by bytebase on GitHub (bytebase/dbhub), where the source, issues and releases live.

Is it free to use?

Yes — it is free and open source under the MIT licence, which permits use, modification and redistribution, including commercially, with attribution.

Does it need a paid API key?

No LLM key is needed by DBHub itself; your MCP client uses its own model, and your database credentials stay in your DSN/config.

How does it compare to per-database community MCP servers?

Compared with per-database community MCP servers, dbhub's distinguishing focus is: a token-conscious MCP server that connects AI tools to Postgres, MySQL, SQLite and more. Pick it when that focus matches your need; the alternative may suit you better if its broader or different scope is the priority.

How do I get started?

Os outros projetos de Agentes de IA com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se dbhub não for o ideal para você.

openclaw★ 391,6 mil
A personal AI that really does things — on any OS, with your data staying yours.
superpowers★ 294,9 mil
An agentic skills framework & software development methodology that works.
ECC★ 275,2 mil
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
hermes-agent★ 252,0 mil
The agent that grows with you — a Python framework for adaptive AI agents.
deepseek-harness★ 245,5 mil
DeepSeek's plugin-based agent harness where everything is a plugin.

// mais em agents

Mais em Agentes de IA

Projetos de Agentes de IA próximos no catálogo, os mais próximos em estrelas de dbhub: continue explorando dos dois lados dele.

goclaw★ 3,6 mil
OpenClaw rebuilt in Go — multi-tenant AI agent teams with 5-layer security in a single binary.
TradingAgents-astock★ 3,6 mil
A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear deb…
antigravity-sdk-python★ 3,7 mil
Google's Python SDK for building AI agents on the Antigravity platform and Gemini models.
onecli★ 3,6 mil
An open-source sandboxed agent harness for teams — a secured personal agent for every employee.
morphik-core★ 3,7 mil
An open-source multimodal retrieval engine for agent pipelines.
ReMe★ 3,6 mil
A memory management kit for agents — remember me, refine me.

Baixe o dbhub

Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.

Ver no GitHub ↗← Mais ferramentas de Agentes de IA