"Information about magic or magical topics" matching MCP servers:

Gives your AI persistent memory across conversations. Stores facts automatically, finds them by meaning using hybrid search with query expansion, and organizes everything into topics without manual tagging.

An MCP server that enforces a pedagogical workflow to teach topics step by step, using research, decomposition, and spaced retrieval practice.

An improved implementation of persistent memory using a local knowledge graph with a customizable --memory-path. This lets Claude remember information about the user across chats.

Your AI forgets everything between sessions. Rekindle fixes that. For Claude Code users who lose time re-explaining project context every session.

Magic: The Gathering MCP server with card search, rules lookup, deck analysis, and Commander intelligence

Smart memory for AI agents. Solves the Karpathy problem: memories decay, topics are frequency-weighted, one-time questions don't become obsessions. 7 tools. Zero deps.

A local MCP server that maintains a persona profile (contact library) for AI assistants, allowing them to create, search, retrieve, supplement, and correct information about people mentioned in conversations via tools like search_profiles, get_profile, create_profile, update_profile, add_facts, update_fact, and delete_fact.

A personal knowledge hub MCP server that enables LLMs to query structured information about Akib Dabgar's skills, experience, projects, and goals using Dynamic Context Retrieval for efficient context usage.

Gives AI coding agents persistent, evolving knowledge about a codebase, enabling them to store and retrieve observations about architecture, conventions, gotchas, and recent work context.

Enables intelligent semantic conversation routing that automatically branches, maintains, and routes between conversation topics instead of relying on entire conversation histories for context.

Enables MCP clients like Claude Desktop to browse, search, and retrieve archived topics from a private knowledge planet via a secure API.

Exposes tools to ingest FigJam boards, retrieve context summaries, and answer free-form questions about the board content.

Salesforce AgentForce as a traversable MCP knowledge graph. 40 nodes covering Einstein Trust Layer, Agent Topics, Actions, Data Cloud, and Resolution Criteria. 11x fewer tokens than RAG. Free: uvx ckg-agentforce

Connects AI assistants like Cursor and Claude to your local Daylens timeline so they can answer questions about your past work sessions, no cloud or API keys needed.

Provides a read-only semantic layer over an Obsidian vault, enabling queries about projects, decisions, tasks, and related notes.

Enables AI agents to semantically search, ask questions about, and analyze videos, with persistent memory and social media import capabilities.

A public MCP server about Boris Churzin's builds, decisions, and ops doctrine, allowing agents to interrogate his judgment instead of parsing a PDF.

Enables storing and querying structured information about software code entities (classes, functions, files) and their relationships (calls, imports) along with qualitative observations like design decisions and change rationale.

Enables AI agents to record, recall, correct, and forget evidence-backed factual claims with temporal history, while explaining whether remembered information is current, historical, or contested.

A version-aware cache for web research that stores and serves documentation references, preventing models from re-researching the same topics across sessions.