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.
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.
npx skills add bytebase/dbhub --skill setupgit clone --depth 1 https://github.com/bytebase/dbhubWrote 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.
[](https://agentmods.dev/skills/bytebase/dbhub/setup)<a href="https://agentmods.dev/skills/bytebase/dbhub/setup"><img src="https://agentmods.dev/badge/skills/bytebase/dbhub/setup/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.
<a href="https://agentmods.dev/skills/bytebase/dbhub/setup"><img src="https://agentmods.dev/badge/skills/bytebase/dbhub/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 28 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 40 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 32 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00742 |
| Opus 5.5 | $0.00010 | $0.00297 |
| Sonnet 5.5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
setup 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 27d 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DBHub Setup
The database connection string (DSN) is entered in the plugin's configuration dialog and stored in Claude Code's secure storage. This plugin is read-only and caps results at 1000 rows.
Connecting or changing the database
-
Help the user build their DSN if they don't have one:
- PostgreSQL:
postgres://user:password@localhost:5432/dbname - MySQL:
mysql://user:password@localhost:3306/dbname - MariaDB:
mariadb://user:password@localhost:3306/dbname - SQL Server:
sqlserver://user:password@localhost:1433/dbname - Oracle:
oracle://user:password@localhost:1521/FREEPDB1(path is the service name) - SQLite:
sqlite:///absolute/path/to/database.db(no credentials)
Append
?sslmode=requirefor SSL (sslmode=disablefor local databases). URL-encode special characters in the password. Recommend a least-privilege, read-only database account. Full DSN options (SQL Server named instances/NTLM, PostgreSQL cert verification): https://dbhub.ai/installation - PostgreSQL:
-
Point them at the config dialog: run
/plugin, open dbhub → configuration, and set the connection string there. The user should not paste the password into the chat. -
Reconnect: run
/mcpand reconnect thedbhubserver (or restart Claude Code).
Troubleshooting a failing connection
- Test the DSN outside the plugin (redact the password in anything shown in chat):
A JSONecho '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"setup-check","version":"0"}}}' | DBHUB_DSN='<dsn>' npx -y @bytebase/dbhub@latest --transport stdio --config <plugin-root>/dbhub.tomlinitializeresponse means the config parsed and the server started; a connection error points at host/port/credentials/SSL. - Common causes: database unreachable from this machine (host/port, VPN, firewall), wrong
sslmode, un-encoded special characters in the password, a SQLite path that isn't absolute. - If the server dies instantly with
sh: dbhub: command not found, the npx cache entry is corrupted (concurrent npx runs can race during install). Find and remove the entry for@bytebase/dbhubunder~/.npm/_npx/*/package.json, then reconnect — npx will reinstall it cleanly. - Requires Node.js >= 22.5.0 (
node --version).
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.
- 27d ago Changed · +1 lines bfb471a306ef
- 1mo ago First seen · 44 lines · 26 tokens per session scan A fbaf3af845ec
setup is a skill published in the GitHub repository bytebase/dbhub (3,664 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 742 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
Audit Database
Comprehensive audit of the Supabase PostgreSQL database. Use when asked to audit, review, or assess the database — covering schema design, RLS policies, multi-tenancy isolation, indexes, migrations, data integrity, and query performance.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.
projection-patterns
Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.