Pokemon Chat
基于 LightRAG、LangGraph、MCP、RagFlow、微调LLMs宝可梦主题的智能聊天助手
What is Pokemon Chat?
Pokemon Chat is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 基于 lightrag、langgraph、mcp、ragflow、微调llms宝可梦主题的智能聊天助手
基于 LightRAG、LangGraph、MCP、RagFlow、微调LLMs宝可梦主题的智能聊天助手
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 基于 LightRAG、LangGraph、MCP、RagFlow、微调LLMs宝可梦主题的智能聊天助手
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pokemon-chatConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Pokemon Chat
Pokemon Chat is a full-stack AI chat assistant built around Pokémon lore, combining LightRAG graph-based retrieval, LangGraph agent orchestration, vector search via Milvus, Neo4j knowledge graphs, and optional MCP integration for geolocation mapping. It uses fine-tuned LLMs and multiple retrieval strategies — vector similarity, graph traversal, and BM25 keyword matching — to answer Pokémon-themed questions with deep contextual accuracy. The project is designed for developers exploring RAG architectures and knowledge-graph-enhanced chat systems in a fun, well-defined domain.
Prerequisites
- Docker and Docker Compose (all services run as containers)
- An LLM provider API key such as SILICONFLOW_API_KEY for inference
- Optional: Tavily API key (tavily_api_key) for web search capability
- Optional: FunASR endpoint (funasr_url) for speech-to-text support
- Git to clone the repository
Clone the repository
Download the Pokemon Chat source code to your local machine.
git clone https://github.com/skygazer42/pokemon-chat.git
cd pokemon-chatCreate and configure the environment file
Copy the example env file and fill in your LLM API key and any optional service keys. Set enable_knowledge_graph=true and enable_knowledge_base=true to activate Neo4j and Milvus.
cp .env.example .env
# Edit .env:
# SILICONFLOW_API_KEY=your_llm_api_key
# llm_api_key=your_llm_api_key
# enable_knowledge_graph=true
# enable_knowledge_base=true
# enable_web_search=false
# tavily_api_key=your_tavily_key # if web search enabledStart the full infrastructure stack
Launch all services including the backend API, Neo4j, Milvus, and the Vue frontend using Docker Compose.
cd docker
docker compose --profile infra up -d --buildEnable the MCP service (optional)
To activate MCP-based geolocation mapping tools, add the mcp profile when starting the stack.
docker compose --profile infra --profile mcp up -d --buildImport Pokémon map data
After the API container is running, import the optional Pokémon map data to enable location-based queries.
docker compose exec api python scripts/import_pokemon_map.pyAccess the chat interface
Open a browser to the web UI. The API documentation is also available for direct integration testing.
# Web UI: http://localhost:3100/
# API docs: http://localhost:5050/api/docsPokemon Chat Examples
Client configuration
The MCP service within Pokemon Chat can be connected to an external MCP client via its SSE endpoint once the mcp profile is running.
{
"mcpServers": {
"pokemon-chat": {
"url": "http://localhost:8080/sse"
}
}
}Prompts to try
Ask the Pokémon chat assistant questions that leverage its knowledge graph and retrieval capabilities.
- "What type advantages does Charizard have against Water-type Pokémon?"
- "Where can I find Snorlax on the Pokémon map?"
- "Explain the evolutionary chain of Eevee and all its possible evolutions"
- "Which Pokémon are found exclusively in the Johto region?"
- "Compare the base stats of Mewtwo and Mew"Troubleshooting Pokemon Chat
Docker Compose fails to start Milvus or Neo4j containers
Ensure Docker has at least 8 GB of RAM allocated (Milvus is memory-intensive). On Docker Desktop, increase memory in Settings → Resources. Run 'docker compose logs milvus' to see specific errors.
Chat responses are slow or LLM calls time out
Verify that SILICONFLOW_API_KEY (or llm_api_key) is valid and the SiliconFlow service is reachable. If using a different LLM provider, update the API base URL in .env accordingly.
Knowledge graph queries return no results
Confirm that the Neo4j data was imported from resources/data/kg_data/entities.json and relations.json. Check Neo4j logs with 'docker compose logs neo4j' and verify enable_knowledge_graph=true in .env.
Frequently Asked Questions about Pokemon Chat
What is Pokemon Chat?
Pokemon Chat is a Model Context Protocol (MCP) server that 基于 lightrag、langgraph、mcp、ragflow、微调llms宝可梦主题的智能聊天助手 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Pokemon Chat?
Follow the installation instructions on the Pokemon Chat GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Pokemon Chat?
Pokemon Chat works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Pokemon Chat free to use?
Yes, Pokemon Chat is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Pokemon Chat Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Pokemon Chat? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Pokemon Chat in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Pokemon Chat?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.