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 neverinfamous/mysql-mcp --skill mysql-routergit clone --depth 1 https://github.com/neverinfamous/mysql-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/neverinfamous/mysql-mcp/mysql-router)<a href="https://agentmods.dev/skills/neverinfamous/mysql-mcp/mysql-router"><img src="https://agentmods.dev/badge/skills/neverinfamous/mysql-mcp/mysql-router/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/neverinfamous/mysql-mcp/mysql-router"><img src="https://agentmods.dev/badge/skills/neverinfamous/mysql-mcp/mysql-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00084 | $0.01451 |
| Opus 5 | $0.00042 | $0.00726 |
| Sonnet 5 | $0.00017 | $0.00290 |
| Haiku 4.5 | $0.00008 | $0.00145 |
Grade A, and why
mysql-router 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MySQL Router Production Standards
MySQL Router is lightweight middleware providing transparent routing between applications and MySQL servers, purpose-built for InnoDB Cluster high availability.
1.1 Architecture & Bootstrap
- Bootstrap-First: [ALWAYS] use
mysqlrouter --bootstrap user@primary:3306 --directory /etc/mysqlrouter --user mysqlrouterfor InnoDB Cluster deployments. Bootstrap auto-discovers topology, creates internal router accounts, generatesmysqlrouter.conf, and registers the router inmysql_innodb_cluster_metadata. - Never Manual for Clusters: [NEVER] manually configure cluster node addresses in
mysqlrouter.conf. Always rely on bootstrap + metadata cache for automatic failover discovery. - Metadata Cache: Router maintains a persistent connection to the cluster, polling
performance_schemafor topology changes. Tune the TTL (e.g.,ttl=0.5) for faster failover detection when needed.
1.2 Routing Strategies
| Strategy | Use Case | Default Port |
|---|---|---|
first-available |
Primary writes (fails over to next available) | 6446 (R/W) |
round-robin |
Read distribution across replicas | 6447 (R/O) |
round-robin-with-fallback |
HA reads with fallback to primary | — |
next-available |
Sticky connections | — |
- Read/Write Splitting: Router natively separates write traffic (port 6446 → primary) and read traffic (port 6447 → secondaries). Applications MUST use distinct connection strings for reads vs writes.
- Sidecar Deployment: [ALWAYS] deploy Router as close to the application layer as possible (e.g., as a sidecar container) to eliminate single points of failure and minimize network latency.
1.3 Connection Sharing (8.0.33+ / 8.4 LTS)
- Mechanism: Instead of terminating server connections on client disconnect, idle connections are pooled and reused. Governed by
connection_sharing_delay. - Limitations: Unsupported in
PASSTHROUGHmode. Sessions usingGET_LOCK()orLAST_INSERT_ID()may prevent safe pooling. - MCP Tool:
mysql_router_pool_statusrequiresconnection_sharing=1on at least one route to return data.
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 · 139 lines · 84 tokens per session scan A e3776f1d578c
mysql-router is a skill published in the GitHub repository neverinfamous/mysql-mcp (10 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 1,451 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
supabase-node
Express/Hono with Supabase and Drizzle ORM.
nodejs-backend
Node.js backend patterns with Express/Fastify, repositories.
solr-extending
To build Solr plugins: SearchComponent, QParser, URP, DocTransformer.
spring-data-jpa
Use when generating JPA entities, repositories, queries, or anything touching the persistence layer. Covers entity conventions, N+1 prevention, projections, and query patterns.
spring-data-redis
Use when implementing caching, session storage, rate limiting, or any Redis integration. Covers cache-aside pattern, key naming, TTL strategy, and serialization config.
transactional-patterns
Use when working with @Transactional, multi-step database operations, distributed transactions, or any code that needs atomicity guarantees. Covers propagation rules, isolation levels, read-only optimization, and common pitfalls.