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 agentmods add skills/googleapis/mcp-toolbox/triage-issuesnpx skills add googleapis/mcp-toolbox --skill triage-issuesgit 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/triage-issues)<a href="https://agentmods.dev/skills/googleapis/mcp-toolbox/triage-issues"><img src="https://agentmods.dev/badge/skills/googleapis/mcp-toolbox/triage-issues.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00164 | $0.01811 |
| Opus 5 | $0.00082 | $0.00905 |
| Sonnet 5 | $0.00033 | $0.00362 |
| Haiku 4.5 | $0.00016 | $0.00181 |
Grade A, and why
triage-issues 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Issues (mcp-toolbox)
Triage here is mostly manual labeling. The product: label auto-routes to the owning team
via .github/blunderbuss.yml. Propose only, never mutating the issue; when a call isn't obvious,
ask rather than guess.
Goal
Given an issue number (or several), deliver a triage the maintainer can apply in seconds: labels across the four axes (each with a one-line why), likely duplicates, missing bug info, and a draft comment when one adds value.
Prerequisites
ghauthenticated forgoogleapis/mcp-toolbox, plus the issue number(s). A GitHub MCP server substitutes forghif it isn't available: theghcommands below map to its read/list tools.
Guidance
Read source-of-truth live, not from memory (labels/routing drift):
gh label list --repo googleapis/mcp-toolbox --limit 200: the only valid label names. Never propose one not listed..github/blunderbuss.yml: whichproduct:labels route to which team..github/ISSUE_TEMPLATE/bug_report.yml: required bug fields (for the completeness check).- references/maintainer-playbook.md: the authoritative taxonomy, priority/status definitions, SLO targets, and comment templates. Read it to classify; this skill only adds how to apply them in a propose-only workflow.
Fetch the issue:
gh issue view <n> --repo googleapis/mcp-toolbox --json number,title,body,author,labels,comments,createdAt
Check bot-noise first. Automated reports (e.g. "Cloud Build Failure Reporter ... failed",
bot author) just need periodic-failure, so skip the rest of the workflow.
The four axes (the playbook has the definitions; below is only how to apply them here). Skip an axis when it doesn't apply: say so, don't force a label.
type:: the template pre-appliestype: bug/type: question; trust it, but correct it when the body disagrees (a "bug" asking for new behavior is a feature request) and say why.product:: one per data source; highest-leverage label, since it drives team routing. Infer from the source/tool named (e.g. "looker run_dashboard tool" →product: looker). Don't force one on core/product-agnostic issues; note it has no product owner. If a real data source has no matching label yet, say so and flag it for.github/labels.yamlrather than mis-routing.priority:: bugs are only ever p0 or p1 (never p2/p3); feature requests span p0-p3. Match the issue to the playbook's priority examples and SLO table, state the reason, and let the maintainer override.status:(optional):waiting for responsewhen a bug lacks info to act,feedback wantedwhen waiting on community/author,help wantedfor community-open work. See the playbook for exact semantics and the >60-day-silence close rule.
What ships with it
1 file 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.
- 5d ago First seen · 128 lines · 164 tokens per session scan A 88b8b77be296
triage-issues is a skill published in the GitHub repository googleapis/mcp-toolbox (16,316 stars, last pushed today), licensed Apache-2.0. It adds 164 tokens to every session and 1,811 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
benchling-integration
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
agentfield
Design and ship a multi-agent system on AgentField. Use when the user asks to build, scaffold, design, or run an agent, reasoner network, multi-agent backend, or 'an agent that does X' — whenever the work would otherwise be a single LLM call or a flat LangChain/CrewAI/AutoGen chain. The skill produces composite…
agentfield-personal
Build and install a personal AI agent on this machine's AgentField: real source in /agentfield-agents, packaged with agentfield-package.yaml, installed with af install, started with af run, registered on the local control plane, and visible in AgentField Desktop with a keys form and an auto-start toggle. Use when the…
openloomi-api
OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth…
sql-best-practices
Use this skill when writing SQL queries — selects, joins, aggregations, window functions, or schema modifications. Apply whenever SQL is needed to ensure correctness, safety, and performance.