MCP Toolbox for Databases is an open-source Model Context Protocol server that connects AI agents, development environments, and applications to enterprise databases through ready-made or custom tools. It is for exploring schemas, querying data, generating code, and building specialized database tools for production agents. The catalogue includes its skills, instructions, and MCP server integration.
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 googleapis/mcp-toolbox --skill review-prsgit clone --depth 1 https://github.com/googleapis/mcp-toolboxWrote 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/googleapis/mcp-toolbox/review-prs)<a href="https://agentmods.dev/skills/googleapis/mcp-toolbox/review-prs"><img src="https://agentmods.dev/badge/skills/googleapis/mcp-toolbox/review-prs/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/googleapis/mcp-toolbox/review-prs"><img src="https://agentmods.dev/badge/skills/googleapis/mcp-toolbox/review-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00162 | $0.03523 |
| Opus 5 | $0.00081 | $0.01761 |
| Sonnet 5 | $0.00032 | $0.00705 |
| Haiku 4.5 | $0.00016 | $0.00352 |
Grade A, and why
review-prs 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 9d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PRs (mcp-toolbox)
A review here is a proposal the maintainer edits and posts, not a rubber stamp. The value is a fast, grounded read of the diff against the team's conventions.
Goal
Given a PR number or link, deliver a review the maintainer can post in seconds: a suggested verdict (approve / request changes / comment), the findings that back it grouped by severity so the important things aren't buried, and a paste-ready summary comment.
Prerequisites
ghauthenticated forgoogleapis/mcp-toolbox, plus the PR number(s). A GitHub MCP server substitutes forghif it isn't available: theghcommands below map to its read/list tools.
Workflow
Step 1: Read the source of truth
Read these live, not from memory. All three are symlinks to the repo-root
files, so they track main; cite them by their root names.
- references/maintainer-playbook.md: Reviewer's Checklist,
SLO/release context,
release candidatelabeling. - references/CONTRIBUTING.md: title/scope format (Conventional
Commits, with the
typetable), keep-PRs-small, link-an-issue. Cite for title, description, and process findings. - references/DEVELOPER.md: tool/source naming, error taxonomy, the
patterns for adding a source/tool/integration test, CI-enforced docs structure, local
test/lint commands. Cite for code, test, and docs findings. Prefer it over
GEMINI.md(CLAUDE.md/AGENTS.mdsymlink to it), which only summarizes.
Step 2: Fetch the PR, its diff, and its checks
gh pr view <n> --repo googleapis/mcp-toolbox --json number,title,body,author,labels,files,additions,deletions,commits,baseRefName,headRefName,state,isDraft,reviewDecision
gh pr diff <n> --repo googleapis/mcp-toolbox
gh pr checks <n> --repo googleapis/mcp-toolbox
Step 3: Triage before reviewing
Three shapes end the review early or change its bar:
- Auto-generated (
renovate,release-please): the only question is whether checks are green. If so, propose merge and stop. - Draft (
isDraft): review lightly and say so; the author isn't asking for a final pass. - Non-code / policy (third-party badge, backlink, promotional README line, often a drive-by
contributor): acceptance is a maintainer policy call, not a code question. Say that plainly
instead of manufacturing code findings, and still check title convention and CI. Mark any URL
you haven't fetched
[UNVERIFIED].
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 254 lines · 162 tokens per session scan A 356b3ea8491f
review-prs is a skill published in the GitHub repository googleapis/mcp-toolbox (16,330 stars, last pushed today), licensed Apache-2.0. It adds 162 tokens to every session and 3,523 once invoked, about $0.0008 per session on Opus 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
qa-review
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
commit
Prepare and create git commits for dynobox. Use this skill whenever the user asks to commit, create a commit, suggest a commit message, stage changes, or prepare changes for review. Also use it when the user asks whether the changelog should be updated before committing.
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.
debug
Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…
speckit-review-tests
Test coverage quality analysis — behavioral coverage, critical gap identification, test resilience evaluation.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…