MCP.so
Sign In

MCP Waifu Chat Server

@waifuai

Repository

About MCP Waifu Chat Server

FastMCP server for conversational AI waifu with user management, dialog CRUD (get/set/reset), OpenRouter API integration, SQLite persistence, and modular extension architecture.

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-waifu-chat": {
      "command": "python",
      "args": [
        "-m",
        "uv",
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Waifu Chat Server?

MCP Waifu Chat Server implements a basic MCP server for a conversational AI “waifu” character. It uses the Python MCP library and FastMCP, providing user management, dialog history storage, and chat via the OpenRouter API.

How to use MCP Waifu Chat Server?

Clone the repository, install Python 3.10+ and uv, create a virtual environment, and install dependencies. Configure your OpenRouter API key (via OPENROUTER_API_KEY environment variable or ~/.api-openrouter file) and optional .env settings. Then run uv run mcp-waifu-chat to start the server.

Key features of MCP Waifu Chat Server

  • User management (create, check, delete, count)
  • Dialog history storage (get, set, reset)
  • Chat via OpenRouter API
  • SQLite database for persistence
  • Modular design for easy extension
  • Comprehensive unit tests

Use cases of MCP Waifu Chat Server

  • Building a conversational AI character for MCP clients
  • Managing multiple user chat sessions with persistent history
  • Prototyping and testing waifu chatbot interactions
  • Extending the server with custom AI providers or genres

FAQ from MCP Waifu Chat Server

What dependencies are required?

Python 3.10+, uv package manager, and an OpenRouter API key.

How do I configure the API key?

Set the OPENROUTER_API_KEY environment variable, or create a single-line key file at ~/.api-openrouter.

What database is used?

SQLite by default. The database file path is configurable via the DATABASE_FILE environment variable (default dialogs.db).

Can I use a different OpenRouter model?

Yes. Set OPENROUTER_MODEL_NAME environment variable or create ~/.model-openrouter file. Falls back to openrouter/free.

How do I run in production?

Use Gunicorn with Uvicorn workers (e.g., gunicorn --workers 4 --bind 0.0.0.0:8000 mcp_waifu_chat.api:app -k uvicorn.workers.UvicornWorker). Consider PostgreSQL, logging, HTTPS, and a reverse proxy.

Frequently asked questions

What dependencies are required?

Python 3.10+, uv package manager, and an OpenRouter API key.

How do I configure the API key?

Set the `OPENROUTER_API_KEY` environment variable, or create a single-line key file at `~/.api-openrouter`.

What database is used?

SQLite by default. The database file path is configurable via the `DATABASE_FILE` environment variable (default `dialogs.db`).

Can I use a different OpenRouter model?

Yes. Set `OPENROUTER_MODEL_NAME` environment variable or create `~/.model-openrouter` file. Falls back to `openrouter/free`.

How do I run in production?

Use Gunicorn with Uvicorn workers (e.g., `gunicorn --workers 4 --bind 0.0.0.0:8000 mcp_waifu_chat.api:app -k uvicorn.workers.UvicornWorker`). Consider PostgreSQL, logging, HTTPS, and a reverse proxy.

Comments

Basic information

Category

AI & Agents

License

MIT-0

Transports

stdio

Author

waifuai

More AI & Agents MCP servers

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

Open Multi-Agent Canvas

CopilotKit

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

507

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797

1MCP - One MCP Server for All

1mcp-app

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

468