"Most Used Minecraft Plugins (MCP)" matching MCP servers:

Enables agents to run hybrid dense and BM25 search over a local folder of Markdown files, read and write notes, and trigger reindexing as the folder changes. It also injects the most relevant sections into each prompt automatically and runs entirely locally with a bundled embedding model.

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 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.

Provides persistent cross-session memory for Claude and other AI agents, letting them store and automatically retrieve decisions, patterns, and knowledge across conversations, restarts, and context limits. It can be self-hosted on Redis or Valkey, or used through a managed SaaS.

Enables MCP clients such as Claude Code to give LLM agents long-term memory by exposing remember, recall and forget tools over stdio, backed by a hybrid BM25 and vector store that reinforces frequently used memories.

Enables semantic search across a document knowledge base, returning the most relevant chunks with relevance scores, and optionally generating written answers with cited sources via an LLM.

Exposes a shared long-term memory store over the Model Context Protocol so that Trae, WorkBuddy, and any other MCP client can save, search, list, fetch, and forget memories in the same on-disk JSONL store used by the DSH plugin, with no need to run DSH. Supports keyword plus local-vector semantic retrieval, project/global scoping, and cross-process locking so records written by any client are immediately visible to the others.

Enables AI clients like Claude Desktop and Cursor to persist project knowledge across sessions and tools by extracting durable facts from conversations, deduplicating them, resolving contradictions, and retrieving only the most relevant, token-budgeted facts for the current task. Adds PII redaction, project scoping, TTL-based staleness handling, and an append-only audit log so shared context stays current and safe.

Enables Claude to query a local, persistent RAG index over markdown folder trees, exposing the same index used by the docrag CLI for on-device, network-free search and retrieval of document chunks via Ollama embeddings.