Look up a URL and prompt in the local cache. Returns cached content instantly if available, or marks a cache miss.
MIT
602,767 tools. Updated 2026-09-23 13:07
"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
- Store a WebFetch result in the cache after a cache miss to persist across sessions, enabling instant cache hits for identical URL and prompt.MIT
- List available LCV Ultrabrain prompt templates for common engineering reasoning workflows, enabling structured thought through step-by-step reasoning, branching, merging, validation, and quality metrics without external LLM APIs.Apache 2.0
- Retrieve cache statistics, including LRU and prompt cache metrics, to monitor and optimize context compression performance.MIT
- Clear the prompt classification cache so the router re-evaluates tasks with current model availability and cost.MIT
Matching MCP Servers
- AlicenseAqualityCmaintenanceA minimal MCP server that exposes Gemini's web and multimodal understanding (video, audio, document, image) through five dedicated tools.51MIT
- AlicenseNot gradedqualityBmaintenanceMCP server for multimodal understanding and object grounding (bounding boxes) across images, videos, and documents, with support for multiple AI providers (Zhipu GLM-V, OpenAI GPT-4o, Anthropic Claude, or any OpenAI-compatible endpoint).1MIT
Matching MCP Connectors
LLM caching proxy (x402 USDC on Base) - exact + semantic cache. Free health.
27 engineering compliance and calculation tools for the built environment (UK, EU, UAE).
- 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
- 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
- Cache a dataset or asset locally for faster subsequent downloads without creating execution or provenance records, ideal for warming the cache before experiments.Apache 2.0
- 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
- Clear website cache instantly after content updates or major changes, purging Hostinger CDN cache when enabled. Specify a directory to clear cache for a WordPress subdirectory installation.MITDestructive
- Identify chords from existing notes in a region for harmonic analysis or reverse-engineering. Groups notes sounding together and matches them to known chord types.Apache 2.0
- 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
- Retrieve soft-deleted prompt snippets to identify restore candidates for recovery.MIT
- Find available calculators and engineering models on MetaModel, returning project names, descriptions, tokens, and model names.MIT
- Retrieves KV-cache utilization, prefix-cache hit rate, and preemption count to monitor inference cluster health and diagnose performance issues.MIT
- Look up the official UNECE Rec. 20 engineering unit symbol for any unit description. Always verify before specifying a unit in industrial modeling to avoid errors.Apache 2.0
- Create a new cached document from a prompt string, assigning a unique key for later retrieval and reuse.MIT