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 joyous-coder/universal-db-mcp --skill db-connectgit clone --depth 1 https://github.com/joyous-coder/universal-db-mcpWrote 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/joyous-coder/universal-db-mcp/db-connect)<a href="https://agentmods.dev/skills/joyous-coder/universal-db-mcp/db-connect"><img src="https://agentmods.dev/badge/skills/joyous-coder/universal-db-mcp/db-connect/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/joyous-coder/universal-db-mcp/db-connect"><img src="https://agentmods.dev/badge/skills/joyous-coder/universal-db-mcp/db-connect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.05640 |
| Opus 5.5 | $0.00032 | $0.02256 |
| Sonnet 5.5 | $0.00016 | $0.01128 |
| Haiku 4.5 | $0.00008 | $0.00564 |
Grade A, and why
db-connect 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 2mo 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
db-connect (universal-db-mcp)
Comprehensive skill for the @joyous-coder/universal-db-mcp MCP server (~485 tests passing).
When to use this skill
Triggers (ANY of):
- User mentions database, query, SQL, schema, table, run a query
- User asks to connect to, inspect, or analyze a database
- User wants to count rows, fetch data, dump, or back up
- User asks about multi-DB management, profile routing, or SQL audit
- User wants to lint SQL, view query history, or get EXPLAIN plans
- User asks about PII masking, schema diff, or index advice
- MCP server is configured AND user asks for any of the above
Auto-configure triggers (use to set up the server itself):
- User says "I need to connect to a database" but no MCP server is reachable
- Project has a
.env,docker-compose.yml, or config file with DB credentials - User mentions a specific DB (mysql / postgres / oracle / dameng / mongodb / ...) and wants to query it
What's in the box
| Capability | MCP tools | HTTP endpoints |
|---|---|---|
| Single-DB connect / execute / list / schema | connect_database, execute_query, list_tables, get_schema |
/api/connect, /api/query, /api/tables, /api/schema |
| Observability (Prometheus metrics, slow query ring) | get_metrics |
GET /metrics, GET /api/health |
| Query experience (Explain, Lint, History, Templates) | explain_query, lint_sql, get_query_history, save_template, list_templates, get_template, delete_template, execute_template |
/api/lint, /api/explain, /api/query-history, /api/templates (CRUD + execute) |
| Multi-database profiles | save_profile, list_profiles, get_profile, delete_profile, use_profile, list_live_profiles, get_global_schema |
/api/profiles (CRUD), /api/profiles/:name/connect, /api/profiles/:name/execute, /api/global-schema |
| Multi-profile (encryption + cross-profile) | Same as multi-DB + profileName filter on templates / history + groupBy: 'profile' aggregate |
mirror + profileName query param |
| Profile Hardening (YAML export/import, Key rotation, History FTS5) | export_profiles, import_profiles (YAML/JSON); rotateKey is internal; history.query accepts q for FTS5 |
mirror |
| Data Governance (Schema diff / Backup / Audit / PII) | compare_profile_schemas, export_backup, audit_log, get_pii_config, set_pii_config |
/api/profiles/:a/compare/:b, /api/profiles/:name/backup, /api/audit-log, /api/profiles/:name/pii |
| Index Advisor + Plan Diff + Plan History | explain_query_with_advice, compare_query_plans, list_query_plans |
/api/query-explain-advice, /api/query-plan-diff, /api/query-plans |
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.
- 2mo ago First seen · 438 lines · 79 tokens per session scan A 324e3317e0d5
db-connect is a skill published in the GitHub repository joyous-coder/universal-db-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 79 tokens to every session and 5,640 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
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.
platform-custom-field-generate
Use when users create, generate, or validate Salesforce Custom Field metadata. Trigger on custom fields, field types, Roll-Up Summary, Master-Detail/Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from a field, or scoping picklist values per record type; also…
field-service-sobject-create-configure
Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
nornicdb-grpc
Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…
output-dev-credentials
Store and reference encrypted secrets in Output SDK workflows using @outputai/core/credentials. Use when integrating API keys, database passwords, or third-party tokens.