"Equipment or items used in windsurfing" matching MCP servers:

Persistent memory and pattern learning for AI coding assistants via MCP.

Enables agents to optimize context-window attention by reordering retrieved documents so critical evidence lands at prompt boundaries, mitigating lost-in-the-middle degradation. It combines BM25 lexical scoring, dense vector similarity, reciprocal rank fusion, knowledge-graph expansion, and recency-decay memory caching, exposed as a zero-dependency MCP stdio server.

Enables agents to run hybrid retrieval, reciprocal rank fusion, knowledge graph expansion, semantic caching, and context reordering so critical evidence is placed at prompt boundaries to reduce lost-in-the-middle degradation.

Enables personal knowledge management through Claude Desktop, allowing users to capture thoughts, connect ideas, and reflect on thinking changes via natural conversation.

Local-first MCP server that extracts structured knowledge from markdown notes into SQLite with full-text search, enabling AI coding tools to retrieve relevant context offline at zero cost.

A local catalogue of the AI tools people share in group chats: search it, save links, vote out junk, and file items into your own folders. Works with any model or none.

Your team's prompt, rules, skills & docs library exposed over MCP (search_library + get_item); mark items "/" and they become slash commands. Free for individuals.

Enables AI assistants to answer high-trust sales questions with cited, vetted facts or explicit refusals, grounded in a local knowledge base.

An MCP server for the Zotero Web API v3 that lets you search, read, and write items, collections, tags, and notes in a Zotero library, supporting literature-review workflows.

Connects AI assistants to Tacit building digital twins to query buildings, equipment, sensors, and zones using natural language. It provides tools for exploring Brick-compliant knowledge graphs, fetching historical sensor data, and accessing site documents.

Provides MCP tools to read, write, append, and edit prose sections of nodes, backed by an in-memory or substrate-direct (Urania) backend.

Enables LLMs to maintain persistent memory by reading and writing Markdown notes and sibling image assets in a user-selected local or sync folder, with no cloud service, account, or server to run.

Provides spaced-repetition scheduling with the SM-2 algorithm as MCP tools, enabling agents to manage review items like flashcards or vocab locally. It supports adding, grading, and listing due items, plus optional pro features for export and forecast.

A simple MCP server for tracking a home bar's inventory and cocktail recipes, with tools to manage shelf items and recipe details.

Repository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.

Enables AI agents to persist facts with tags, sources, and importance in a local SQLite database, retrieve them through hybrid BM25 plus embedding search weighted by retention decay, link or supersede related entries, and review everything in a read-only visual dashboard showing the memory graph and timeline.

MCP server for ContextKeeper that enables AI assistants to read and modify context items through natural language commands.

Enables MCP clients to search a Zotero library, read items, take notes, organize collections, and perform semantic search over PDFs.

Enables AI agents to search and navigate a computer science concept ontology, map exam items to concepts, rank shared prerequisites, and run multi-step wrong-answer diagnosis with review ordering.

MCP server exposing a deterministic, local knowledge graph over stdio. Zero LLM calls in the bridge; answers are classified as Fact, Inference, or Unknown and persisted in redb (ACID, BLAKE3-hashed).

MCP server for managing personal items with expiration dates, enabling AI agents to add, query, and scan barcode items via API Key authentication.

An MCP server for IT Glue that provides 56 tools for managing organizations, configurations, passwords, documents, flexible assets, contacts, locations, users, groups, attachments, related items, and bulk operations, with built-in rate limiting, caching, and security guards.

A flexible memory system for AI applications that supports multiple LLM providers and can be used either as an MCP server or as a direct library integration, enabling autonomous memory management without explicit commands.

An MCP server that enables Claude to learn from user corrections by recording them as persistent rules in CLAUDE.md files. It manages project-specific or global guidelines to ensure the assistant avoids repeating the same mistakes in future sessions.

Enables cataloguing small household items with location notes, tags, and photo hints, then searching for them, checking where they are, listing by room, and recording moves through MCP tools.

Enables interaction with Zotero libraries for searching, managing collections, items, tags, and attachments, plus optional semantic search across PDFs via local embeddings.

An MCP server that lets AI assistants add papers and books to your Zotero library by DOI, arXiv ID, or ISBN, and manage your collections, tags, and items.

Turns arXiv and LaTeX mathematical papers into theorem dependency graphs, exposing MCP tools to load papers, list theorems, get theorem details, find dependencies, and locate where theorems are used.

Gives AI agents a persistent long-term memory store over MCP, letting them remember facts and preferences, recall ranked memories with a one-line explanation of why each scored, mark which recalled memories were used or ignored so retrieval learns over time, and forget or list memories per namespace.

Read and search the Urantia Papers in English and Spanish by reference, keyword, or meaning, with named entities and cross-references to the Bible and 21 other texts.

Enables AI assistants to read, search, and write Markdown notes kept in Postgres, alongside a web app with a file tree, wikilinks, full-text search, and a graph. Supports OAuth or API-key connections, per-account vaults, and folders shared with other people read-only or read-write.

An offline-first, governed memory and knowledge server for AI agents that provides Remember, Search, Update, and Forget operations with hybrid retrieval, semantic embeddings, and NID-based authentication. It can be used as an MCP server via stdio or Streamable HTTP, enabling agents to persist and query memories and wiki knowledge.

Exposes 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client like Claude Code, Cursor, or Cline.

Enables AI agents to search, read, and act on a permanent archive of Bee wearable data—conversations with transcripts, daily recaps, insights, todos, facts, voice notes, places, and photos—stored in the user's own Cloudflare account. Agents can query any day, find conversations by person or topic, and create or manage todos and facts through 33 tools.

Persistent decision memory and contradiction detection for AI coding agents. Enforces architectural consistency across sessions — the agent cannot code until it loads prior decisions. Human resolves conflicts on a dashboard or in chat.

A Git-backed MCP relay that lets multiple AI assistants share one local Markdown notes vault, recording which app, model and reasoning setting made each edit. It versions every change in Git and holds suspicious prompt-injection attempts or large deletions in a quarantine for human review.

Privacy-first personal knowledge database for your AI that ingests data exports (Google Takeout first) and exposes them via MCP tools like search and list items. Runs locally with no cloud or telemetry.

Gives an entire household one shared memory, so each member's needs are remembered across days and across people, with follow-ups and confirmation before anything is written. Enables adding needs, briefing a speaker on others' open items, previewing and confirming additions to errand runs, and marking needs done.

Enables MCP-compatible AI agents to access wearable device status and recent diarized transcripts, search semantic memory, retrieve commitments and action items, and dispatch autonomous task workflows.

A lightweight MCP sidecar exposing safe, read-only Anchor note tools to ChatGPT via a tunnel client in the same Docker stack. It currently supports listing, searching, reading notes, tags, and attachment metadata without exposing Anchor's private API or database.