"Understanding Cache for Prompt Engineering" matching MCP servers:

MCP 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).

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

Enables AI models to interactively prompt users for input or clarification directly through their code editor. It facilitates real-time communication between assistants and users during development tasks.

Exposes get, set, and delete operations over a Redis/Valkey-compatible key-value store as MCP tools, with per-user key namespacing and TTL support on writes. Enables clients to cache and retrieve arbitrary string values statelessly over SSE or direct HTTP, using their own backend.

Provides a local SQLite cache of package documentation and APIs, enabling AI coding assistants to access dependency context offline with sub-10ms latency via MCP.

MCP server that enables AI coding assistants to audit repositories against engineering rules, generating self-contained HTML reports with citations and optional GitHub issue filing.

Reduces token consumption by over 80% through intelligent file caching, returning only diffs for modified files and suppressing unchanged content. It features a suite of 12 tools for semantic search, batch reading, and efficient file editing to optimize LLM interactions with large codebases.

Lets AI agents gate actions before they happen with allow/ask/deny verdicts, rank up to 255 options, and report decision stats.

27 deterministic engineering compliance and calculation tools for the built environment (data-centre PUE and EED, EPBD, NIS2, Eurocode, UAE compliance), callable by AI agents via MCP and REST API. Free tier; every result cites the governing standard.

An MCP server that analyzes local or remote GitHub repositories, providing intelligent code context and structure to AI coding assistants.

Connects LLMs to Israeli civil engineering databases, including the Blue Book specs, Dekel 2026 pricing, Excel BOQ parsing, and tender arbitrage for unbalanced bidding.

Provides access to your Amplenote SQLite database cache, enabling search and retrieval of notes and tasks, including full-text search, bidirectional references, task filtering by priority and due dates, and recently modified content tracking.

Provides a local MCP interface to query captured, PII-scrubbed prompt telemetry from coding agents and browser chats, enabling time summaries, prompt search, and activity analysis without data leaving the machine.

Integrates Xiaomi MiMo's multimodal API to enable understanding of images, audio, and video through natural language prompts.

Enables dynamic prompt management by automatically discovering and serving markdown prompt files with YAML frontmatter via the Model Context Protocol.

A lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.

Enables local and offline XLSX header cataloging, candidate relationship inference, and Oracle SELECT/WITH SQL generation without accessing databases or executing SQL.

An MCP server that allows agents to test and compare LLM prompts across OpenAI and Anthropic models, supporting single tests, side-by-side comparisons, and multi-turn conversations.

Smart AI workflow for Cursor teams with intelligent prompt routing, real-time cost optimization, and team analytics.

Enables MCP-compatible AI clients to store and recall voice conversation context by caching user and AI utterances, supporting formatted context summaries for multi-turn voice interactions.