Waifu Queue MCP Server

Generates asynchronous text responses using a distilgpt2 model, managed through a Redis queue and accelerated with GPU support, exposing an

Local serverstdioPython 1

What is the Waifu Queue MCP server?

If you already use Waifu Queue, the waifu queue mcp server is the piece that lets your assistant work with it directly. Generates asynchronous text responses using a distilgpt2 model, managed through a Redis queue and accelerated with GPU support, exposing an MCP-compliant API.

What the server does

This project implements an MCP (Model Context Protocol) server for a conversational AI "waifu" character, leveraging the OpenRouter API via a Redis queue for asynchronous processing. It utilizes the FastMCP library for simplified server setup and management.

  • Text generation via OpenRouter using model from ~/.model-openrouter or openrouter/free
  • Request queuing using Redis for handling concurrent requests asynchronously
  • MCP-compliant API using FastMCP
  • Job status tracking via MCP resources
  • Configuration via environment variables (.env file)
  • API key loading:

Installation

uvicorn on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Description — ** Sends a text generation request to the OpenRouter API via the background queue
  • Input — ** {"prompt": "Your text prompt here"} (Type: GenerateTextRequest)
  • Output — ** {"job_id": "rq:job:..."} (A unique ID for the queued job)
  • Tools — The Tools tool exposed by this server
  • Resources — The Resources tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: OPENROUTER_API_KEY, YOUR_REPOSITORY_URL, REDIS_URL. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Python 3.7+ * pip or uv (Python package installer) * Redis server (installed and running) * An OpenRouter API Key You can find instructions for installing Redis on your system on the official Redis website: https://redis.io/docs/getting-started/ You can obtain an OpenRouter API key from: https://openrouter.ai/

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Where it fits

Plenty of database access servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Waifu Queue's toolset — Description, Input, Output and 2 more — is a fair guide to whether it matches your workflow. It is maintained by waifuai; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
Description** Sends a text generation request to the OpenRouter API via the background queue.
Input** {"prompt": "Your text prompt here"} (Type: GenerateTextRequest)
Output** {"job_id": "rq:job:..."} (A unique ID for the queued job)
ToolsThe Tools tool exposed by this server.
ResourcesThe Resources tool exposed by this server.

How to install the Waifu Queue MCP server

{
  "mcpServers": {
    "waifu-queue": {
      "command": "uvx",
      "args": ["uvicorn"],
      "env": {
        "OPENROUTER_API_KEY": "your-value",
        "YOUR_REPOSITORY_URL": "your-value",
        "REDIS_URL": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • Python 3.7+ * pip or uv (Python package installer) * Redis server (installed and running) * An OpenRouter API Key You can find instructions for installing Redis on your system on the official Redis website: https://redis.io/docs/getting-started/ You can obtain an OpenRouter API key from: https://openrouter.ai/
VariableDescriptionRequired
OPENROUTER_API_KEYCredential the server authenticates with.Yes
YOUR_REPOSITORY_URLEndpoint or connection string the server talks to.Yes
REDIS_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Waifu Queue to Description.
  • Use Waifu Queue to Input.
  • Use Waifu Queue to Output.

Frequently asked questions

While not strictly required, a CUDA-enabled GPU is highly recommended for significantly faster text generation.