Value Proposition Optimize throughput and reduce latency across all database interactions. Empower your AI agents with enterprise-grade connection pooling, secure sandboxed execution, and comprehensive query diagnostics to support multi-agent ecosystems. Read the full value proposition.

Fine-tune the underlying connection pool configuration. This is a key setting. It directly dictates the ceiling of concurrent tool execution. It impacts overall agent responsiveness.

• stdio (single agent): Default 10 works well. AI agents usually issue queries sequentially.
• HTTP Transport (--transport http) (multiple agents): Increase to 20–50. Each tool call needs a connection. Monitor for acquireTimeout errors.
• Short-lived queries: If your workload is mostly reads, a pool of 10–15 handles high throughput because connections are returned quickly.
• Long-running analytics: Increase the pool for complex aggregations holding connections. Consider using Code Mode. It batches work into a single connection.

Configuring REDIS_URL synchronizes rate limits across the HTTP Transport layer and Code Mode sandboxes, governed by MCP_RATE_LIMIT_MAX and CODEMODE_RATE_LIMIT_MAX. Note that the standard stdio transport is local and NOT subject to HTTP rate limits, but Code Mode within stdio still enforces rate limits locally. The architecture includes a graceful fallback to in-memory rate limiting if the Redis instance becomes unavailable.

This distributed rate limiting strategy acts as an essential safeguard for critical database resources, ensuring balanced compute access and ensuring platform stability in multi-agent environments.

Exposing the full tool library simultaneously can unnecessarily increase token overhead.

The --tool-filter CLI flag allows you to selectively mount tools, so you only expose what your specific workload demands.

Avoid mounting the entire toolset simultaneously to prevent performance penalties. Leverage specialized presets like starter or dba-monitor to streamline your agent's context and improve token efficiency.

# Mount only the tools your agent needs
npx -y @neverinfamous/mysql-mcp --tool-filter "starter"

See Tool Filtering for the complete list of groups and shortcuts.

Code Mode (mysql_execute_code) accelerates agent operations, reducing token overhead by intelligently batching complex data pipelines.

• Single-step retrieval: "Get the schema for the users table."
• Simple lookups: "Search for 'payment failed' in the logs."
• Low latency per step: Tool calls are fast. Multi-step reasoning requires multiple LLM roundtrips.

• Multi-step data pipelines: Query tables and process results in JavaScript.
• Maximize Token and Execution Efficiency: Batching complex data pipelines reduces token usage, minimizes network latency of multi-step reasoning loops, and returns only the final answer from the sandboxed environment.

Rule of Thumb: Use Code Mode if a question requires more than two sequential queries.

Diagnose slow queries and optimize execution plans using comprehensive diagnostic prompts rather than standalone tools. These prompts intelligently guide the analysis process.

• mysql_performance_analysis: A comprehensive diagnostic prompt to guide analysis of query execution and performance metrics.
• Other specialized prompts are dynamically available to analyze index usage and table statistics.

Leverage the diagnostic prompts to systematically identify slow queries, analyze query execution plans, check index statistics, and verify optimization improvements.

Telemetry can be monitored in real-time via the Prometheus /metrics endpoint. Visualize them in the Grafana dashboard.

For full setup instructions, see Observability & Telemetry.

Our benchmarks confirm sub-millisecond overhead on critical paths:

Clone the source repository and run pnpm run bench locally for full results on your hardware.

• Capacity Planning - System capacity and scaling
• Tool Filtering - Custom tool filtering
• Code Mode - Code Mode API documentation
• Configuration - General configuration