"Steam Deck" matching MCP servers:

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

Hearthstone MCP server with card search, deck analysis, and strategy coaching. Gives LLMs access to every Hearthstone card plus built-in strategy knowledge for deck building and gameplay advice.

Windows-local MCP for Steam Balatro: tool-calling AI reads player-visible state, chooses and executes native actions, confirms results, and saves local experience. Glama's Linux sandbox can introspect MCP and run game-independent tools such as calculate, but cannot connect to Balatro on the user's Windows machine. Without the local game, health reports disconnected.

Enables AI tools to manage Anki flashcards, including deck management, card search, creation, editing, deletion, and statistics.

Provides a local-first memory layer for coding agents, storing principles, rules, and corrections on-device and surfacing them at the moments they apply so agents act on the intended outcomes without sending data to the cloud.

Exposes Anki as a set of tools for LLM clients, enabling note creation, search, review, and deck management via AnkiConnect.

Local MCP server exposing the dek-memory hybrid memory engine over stdio, with optional ChatGPT tools for managing account memories via a browser profile.

Enables users to sign in with OAuth and build, page through, review, grade, and delete their own private flashcard deck through MCP tools. Per-user isolation is enforced in code, with per-account limits on card count, stored text, and tool calls per minute.

An MCP server for team documentation and knowledge bases, enabling semantic search over documentation files using local embeddings.

Enables LLMs to interact with Anki flashcard collections, including deck management, note search, viewing contents, and editing fields.

Enables multiple Claude agents to share and curate markdown memory files in versioned S3 storage, with conflict-safe reads and writes, attribution, search, and session trace summaries.

Exposes read-only local markdown envelopes through MCP tools for health, context, and recall queries.

Shared team memory for AI coding agents with Bayesian confidence scoring and temporal decay, enabling persistent storage and retrieval of engineering patterns across sessions.

A hosted remote MCP server for OpenAI Codex memory MCP, providing structured JSON tools to store, recall, and manage memory with token-based access and audit receipts.

Read, search, and write Obsidian vault notes via Team Relay collaborative server. Supports shared folders, real-time sync, and AI agent access.

Decision memory for teams building with AI coding agents. Captures every engineering decision once, ranks it by blast radius, and briefs every MCP-compatible agent before it acts, so agents stop making conflicting changes across repos.

Exposes Team Vault's REST API as MCP tools for AI agents, enabling programmatic reading and editing of notes without Obsidian.

Enables AI coding assistants to query and store a team's historical development experience through semantic search, so lessons and decisions persist across conversations.

Enables interaction with the RAGFlow API to manage knowledge base datasets and conduct AI-driven chat sessions. Users can list datasets, create chat assistants, and retrieve or query information from specialized knowledge bases.

MCP server for InvGate Service Desk — manage incidents, users, knowledge base, assets and time tracking from any AI assistant.

Enables coding agents such as Claude Code and Cursor to check a team's learned decisions from pull requests, reviews, and docs before writing code, showing whether breaking them is blocking or advisory. It also provides locally computed symbol impact/blast-radius analysis so source code never leaves the machine.

Provides QE Framework expert-library guidance with compact search and recommendation tools, returning full expert content only on explicit request.

Enables Claude to maintain a team knowledge base stored as markdown in a GitHub repository, with tools for search, edit, linking, and interactive views.

Enables AI assistants to run PubMed searches in plain English, download full-text articles from PubMed Central, and map the similar, citing and cited evidence around key papers. It also builds an Obsidian knowledge graph of a study's literature, with retractions flagged and citations traceable to papers the assistant read.

Every memory framework treats a frequently-used fact as trustworthy forever but "still relevant" and "still true" aren't the same thing.A customer's city, a teammate's role, a project's status: these age quietly, and nothing catches it until an agent confidently repeats something that stopped being true months ago. FactLayer is a lightweight check that sits on top of whatever memory system you.

Enables AI assistants to maintain persistent personal memory in the user's own Google Drive, including save points, rules, projects, decisions, wins, and daily tidy-up. This lets context and preferences carry across chats while keeping stored files user-controlled.