View prompt classification cache statistics: hit rate, entries, memory usage. Monitor cache efficiency and validate cached classifications.
MIT
306,292 tools. Last updated 2026-07-25 05:24
"Understanding Cache for Prompt Engineering" matching MCP tools:
- Detects hidden prompt injection in tool descriptions: file read, exfiltration, instruction override, system prompt extraction, social engineering. Returns findings with pattern and severity.MIT
- List pre-built prompt templates for structured engineering reasoning, enabling step-by-step analysis, branching, and validation without external API calls.Apache 2.0
- Clears the prompt classification cache, resetting cached routing decisions and forcing fresh model selection.MIT
- Discover available prompt engineering techniques with acceptance statistics to enhance AI interactions through optimized method selection.MIT
- Transform prompts using engineering best practices to improve clarity and effectiveness for AI assistants.MIT
Matching MCP Servers
- -license-quality-maintenanceSemantic caching MCP server for AI agent tool calls, providing exact and similarity-based cache lookup, store, invalidation, and metrics via MCP tools.Last updated
- Flicense-qualityCmaintenanceProvides a local SQLite cache of package documentation and APIs, enabling AI coding assistants to access dependency context offline with sub-10ms latency via MCP.Last updated
Matching MCP Connectors
LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
1,177 free agentic trading prompts for Claude and Robinhood MCP.
- Improve prompt quality by applying optimal engineering techniques like chain-of-thought reasoning based on intent analysis.MIT
- Provide answers to clarifying questions to continue prompt engineering for Claude Code, enabling interactive refinement of optimized prompts.MIT
- Fetch and cache all organization users to disk for efficient repeated access.MIT
- Analyze a system prompt for context engineering issues and get top findings ranked by severity. Use for reviewing, improving, or debugging AI agent prompts.MIT
- Generate or modify code files with smart diffs. Provide file path and detailed prompt to create or edit files using context for accurate code generation.MIT
- Report BuildKit cache disk usage as a list of records. Use to identify cache size and reclaim space with buildx_prune.MIT
- Search open bounties for paid engineering work across software, hardware, MCP servers, CAD, EDA. Filter by category, status, and payout to discover tasks matching your capabilities.MIT
- Analyze text content for security threats like command injection, encoding attacks, social engineering, and PII. Returns a JSON report with verdict and threat count for safe processing of untrusted input.MIT
- Lists Engineering Change Notices (ECNs) in a project, with optional filters by severity, status, and type.Apache 2.0
- Monitor cache performance and identify issues with offline browsing by checking health status and statistics for the collection cache system.AGPL 3.0
- Cache runs to disk by fetching with optional filters for repeatable access.MIT
- Show local search cache status with scar count, age, and staleness. Use to monitor cache health and know when to refresh.MIT
- Clear server-side cache for specified browser directories within a workspace to manage cached data.MIT
- Get the Pinker build cache status to verify cache health for single-app and platform modes.MIT