"Kotlin RAG (Retrieval-Augmented Generation) implementation resources" matching MCP servers:

An MCP server that exposes World of Warcraft character data from the Blizzard API, offering read-only tools for character summaries, equipment, Mythic+ scores, realm lookup, and other character sub-resources.

Enables AI assistants to search for games and retrieve aggregated critic scores, review tiers, and individual reviews from OpenCritic. Provides tools for game search, score retrieval, and review lookup via the OpenCritic API.

Exposes Steam Web API tools as MCP resources for Claude Code, Claude Desktop, and Gemini CLI, enabling profile lookups, game searches, achievement tracking, and more.

Enables AI-powered image generation and curation for Foundry VTT tabletop art, letting users create portraits, tokens, handouts, and scene backgrounds from prompts via a local headless ComfyUI workflow.

MCP server for Project CPU, a blockchain game on EVM. It lets an AI agent play on your behalf: read the world map, reveal cells, build and mine, craft, move resources, trade at marketplaces, and cash out to on-chain $CPU.

Provides AI assistants with 69 tools, 19 prompts, and 21 resources for deep access to Magic: The Gathering, including card data, combos, draft analytics, Commander metagame, competitive constructed, sideboard strategy, deck building, and rules engine, working with any MCP client.

An MCP server that provides live status updates for the Eco via Sirens game server, displaying meteor countdowns, player statistics, and world information directly within Claude Desktop. It also serves as a minimal reference implementation for building MCP Apps in Python without complex tooling.

An MCP server that provides tools for rolling dice using standard notation, flipping coins, and selecting random items from lists. It supports advanced tabletop gaming features such as character stat generation and keep-highest/lowest mechanics.

Enables searching and retrieving Minecraft Wiki content in multiple formats (wikitext, HTML, markdown) through MCP tools, with batch retrieval and health monitoring.

MCP server that enables natural language listing, unpacking, and exporting of Unreal Engine game resources via umodel, including AES-encrypted pak support.

MCP server providing true randomness capabilities to Claude, enabling cryptographically secure random number generation for games, decision-making, sampling, simulations, and any operation requiring genuine randomness.

Enables read-only MCP access to an unpacked game data directory, supporting directory listing, paginated text/XML reading, content search, translation lookup, and retrieval of spell/entity definitions without executing Lua or computing derived values.

Enables AI agents to read and edit Godot 4.x scenes and resources, introspect the class API, run the game in a managed headless process with frame stepping, input injection and screenshots, validate scripts, and diagnose code via a built-in GDScript LSP plus a bridge to an already open editor.

Enables playing RPGs with LLMs through tools for dice rolling (e.g., '1d6'), success checks with criticals, and random event generation.

A Model Context Protocol server for querying and analyzing double-color ball (双色球) lottery historical data from 2013 to present, offering tools for data retrieval, statistical analysis, and reference number generation.

Gives LLMs live, accurate access to Team Fortress Wiki content, enabling search, page retrieval, structured weapon stats, patch notes, and other TF2-specific information.

An MCP server that exposes the PokéAPI as tools and resources, allowing AI assistants to look up Pokémon data in real time without configuration.

Enables chess analysis and move generation using the Stockfish engine via MCP tools, allowing clients to evaluate positions, get best moves, apply moves, and visualize boards.

Enables persistent, model-driven text adventures with transactional saves, character knowledge boundaries, cited canon retrieval, dice outcomes, and forkable historical timelines via MCP tools and local SQLite storage.

Gives AI assistants structured access to racing-game telemetry such as lap and sector times, lap comparisons, braking zones and tyre wear through MCP tools and resources. It works out of the box on bundled synthetic sample data and can ingest a live F1 23 UDP feed.