"Connecting Docker to Cursor" matching MCP servers:

Provides Prolog logic programming integration for Claude via a Docker SWISH container, with persistent notebooks and cognitive architecture support.

Engram is a local-first memory server that lets AI agents remember things across sessions with zero cloud dependencies.

Scoped, low-latency persistent memory layer for AI agents, Cursor, and Claude Code over Model Context Protocol with sub-50ms hybrid search.

Provides full access to Hookmark on macOS, enabling users to create and manage bidirectional links between files, URLs, emails, and notes. It supports searching bookmarks, connecting items, and retrieving links from active applications through natural language.

Connect Paste to Claude, Codex, Cursor, and other AI tools to access your clipboard.

Adds persistent memory to AI assistants by connecting to the Memphora cloud platform, allowing them to store and recall facts across conversations. It enables tools for searching memories, extracting insights, and maintaining long-term user context and preferences.

Self-hosted task tracker and MCP server for AI coding agents. Append-only case files preserve decisions, failed attempts, questions, and check results across sessions. A live web board lets people track progress and answer agents. Runs locally in Docker and connects to Claude Code, Codex, Cursor, and other Streamable HTTP MCP clients. MIT licensed.

Enables LLM agents to access a private knowledge base through MCP by automatically chunking and indexing .txt documents, with zero configuration and no Docker or vector database required.

Local-first MCP graph intelligence server providing RRF hybrid search, multi-hop traversal, source snippets, and rationale nodes for AI agents, without Docker or web UI.

MCP server for Yandex Wiki with full-text search. Read and write pages, comments, attachments, and dynamic tables (grids); optional server-side read-only mode for agents. Docker-ready.

MCP server that connects Cursor agents to a local Obsidian vault via the Local REST API, enabling note reading, writing, searching, patching, and organizing through natural language.

Provides OpenCode with adaptive long-term memory by storing preferences, lessons, and usage history locally in SQLite, enabling AI to remember and adapt to users through context-based learning.

MCP server for Chaos Intelligence to access Capture thoughts and Resonate posts from AI tools like Claude and Cursor.

Enables Claude and Cursor to access agent memory, shared knowledge graphs, and decision audit through MCP.

Shared, versioned memory for your agents across Claude Code, Cursor, Kiro and Grok. One MCP server, sourced answers, full history.

MCP server for StudioMeyer Academy that connects Claude Code, Cursor, or Claude Desktop to track learning progress in the Memory-First AI Operator curriculum. It enables users to view lessons, complete quizzes, earn certificates, and run spaced-repetition reviews directly in chat.

Turn Obsidian notes into agent-ready context, preview-only plans, and safe repo handoffs.

This project implements a Model Context Protocol (MCP) server for connecting AI models with Obsidian knowledge bases. Through this server, AI models can directly access and manipulate Obsidian notes, including reading, creating, updating, and deleting notes, as well as managing folder structures.

Real TypeScript MCP server for connecting Zynx agents to Supabase through safe, allowlisted tools.

Provides structured external memory for AI assistants, enabling persistent context, branch notes, tacit knowledge, and checklists to overcome AI memory loss and context confusion.