MCP.so
Sign In

MCP Waifu Queue (Gemini Edition)

@waifuai

Repository

About MCP Waifu Queue (Gemini Edition)

FastMCP server for asynchronous conversational AI using OpenRouter API via Redis queue/worker architecture. GPU inference support, environment-variable configuration, and deployment-ready setup.

#mcp#waifu#queue#conversational-ai#text-generation

Basic information

Category

AI & Agents

License

MIT-0

Runtime

python

Transports

stdio

Publisher

waifuai

Config

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

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

Tools

1

** Sends a text generation request to the OpenRouter API via the background queue.

Overview

What is MCP Waifu Queue (Gemini Edition)?

MCP Waifu Queue (Gemini Edition) is an MCP server for a conversational AI “waifu” character. It uses the OpenRouter API (via a Redis queue) for asynchronous text generation and is built with the FastMCP library.

How to use MCP Waifu Queue (Gemini Edition)?

Install dependencies and configure OpenRouter API key and model selection (via environment variables or home‑directory files). Start a Redis server, then run the RQ worker (python -m mcp_waifu_queue.worker) and the MCP server (e.g., with uvicorn mcp_waifu_queue.main:app). Clients interact with the generate_text tool and the job://{job_id} resource.

Key features of MCP Waifu Queue (Gemini Edition)

  • Text generation via OpenRouter using a configurable model.
  • Request queuing with Redis for asynchronous processing.
  • MCP‑compliant API using the FastMCP library.
  • Job status tracking through MCP resources.
  • API key loading from environment variables or file fallbacks.
  • Pydantic‑based request and response validation.

Use cases of MCP Waifu Queue (Gemini Edition)

  • Building a conversational AI assistant with a predefined character.
  • Queuing long‑running text generation requests without blocking the client.
  • Integrating a waifu chatbot into MCP‑compatible tools and agents.
  • Offloading generation workloads to a background worker for scalability.

FAQ from MCP Waifu Queue (Gemini Edition)

What models can be used?

The server uses the model specified in ~/.model-openrouter or defaults to openrouter/free. You can use any model available via the OpenRouter API.

How do I get an OpenRouter API key?

Obtain a key from openrouter.ai and set it as the OPENROUTER_API_KEY environment variable or place it in ~/.api-openrouter.

What is Redis used for?

Redis is required to queue text generation requests. The RQ worker picks up jobs from the queue and processes them asynchronously.

How can I check the status of a submitted job?

After calling the generate_text tool, you receive a job_id. Use the job://{job_id} MCP resource to retrieve the job status and result.

What are the runtime dependencies?

Python 3.7+, a running Redis server, and the packages listed in requirements.txt. The server also needs an OpenRouter API key and network access to OpenRouter.

Comments

More AI & Agents MCP servers

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

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

MCP-LLM Bridge

patruff

Bridge between Ollama and MCP servers, enabling local LLMs to use Model Context Protocol tools

976

21st.dev Magic AI Agent

21st-dev

It's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic

5.3K

Solon Ai

opensolon

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

416