MCP Waifu Queue

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

Table of Contents

• Features

• Architecture

• Prerequisites

• Installation

• Configuration

• Running the Service

• MCP API

• Testing

• Troubleshooting

• Contributing

• License

Related MCP server: Selector AI FastMCP

Features

• Text generation via provider abstraction:

  • OpenRouter (default) using model from ~/.model-openrouter or deepseek/deepseek-chat-v3-0324:free.

  • Google Gemini supported as fallback or via selection, model from ~/.model-gemini or gemini-2.5-pro.

• 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).

• Provider selection:

  • Default provider: OpenRouter

  • Override via PROVIDER=openrouter or PROVIDER=gemini

• API key loading:

  • OpenRouter: OPENROUTER_API_KEY or ~/.api-openrouter

  • Gemini: GEMINI_API_KEY or GOOGLE_API_KEY or ~/.api-gemini

• Model selection files in home directory:

  • ~/.model-openrouter for OpenRouter model name

  • ~/.model-gemini for Gemini model name

Architecture

The project consists of several key components:

• main.py: The main entry point, initializing the FastMCP application and defining MCP tools/resources.

• respond.py: Contains the core text generation logic using the Google GenAI SDK (google-genai) via the centralized genai.Client.

• task_queue.py: Handles interactions with the Redis queue (using python-rq), enqueuing generation requests.

• utils.py: Contains utility functions, specifically call_predict_response which is executed by the worker to call the Gemini logic in respond.py.

• worker.py: A Redis worker (python-rq) that processes jobs from the queue, calling call_predict_response.

• config.py: Manages configuration using pydantic-settings.

• models.py: Defines Pydantic models for MCP request and response validation.

The flow of a request is as follows:

1. A client sends a request to the generate_text MCP tool (defined in main.py).

2. The tool enqueues the request (prompt) to a Redis queue (handled by task_queue.py).

3. A worker.py process picks up the job from the queue.

4. The worker executes the call_predict_response function (from utils.py).

5. call_predict_response calls the predict_response function (in respond.py), which interacts with the Gemini API.

6. The generated text (or an error message) is returned by predict_response and stored as the job result by RQ.

7. The client can retrieve the job status and result using the job://{job_id} MCP resource (defined in main.py).

Prerequisites

• Python 3.7+

• pip or uv (Python package installer)

• Redis server (installed and running)

• An OpenRouter API Key and or a Google Gemini 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 a Gemini API key from Google AI Studio: https://aistudio.google.com/app/apikey

Installation

1. Clone the repository:

   git clone <YOUR_REPOSITORY_URL> cd mcp-waifu-queue

2. Create and activate a virtual environment using uv:

   python -m uv venv .venv .venv/Scripts/python.exe -m ensurepip .venv/Scripts/python.exe -m pip install uv

3. Install dependencies:

   .venv/Scripts/python.exe -m uv pip install -r requirements.txt .venv/Scripts/python.exe -m uv pip install -r requirements-dev.txt

Configuration

1. Provider Selection:

   • Default provider is OpenRouter. To override, set:

     PROVIDER=openrouter

     or

     PROVIDER=gemini

2. Model Names via files in $HOME:

   • OpenRouter model file:

     echo "deepseek/deepseek-chat-v3-0324:free" > ~/.model-openrouter

   • Gemini model file:

     echo "gemini-2.5-pro" > ~/.model-gemini

3. API Keys: Preferred via environment variables with file fallback:

   • OpenRouter: OPENROUTER_API_KEY or ~/.api-openrouter

   • Gemini: GEMINI_API_KEY or GOOGLE_API_KEY or ~/.api-gemini

   echo "YOUR_API_KEY_HERE" > ~/.api-gemini

   (Replace

4. Other Settings: Copy the .env.example file to .env:

   cp .env.example .env

5. Modify the .env file to set the remaining configuration values:

   • MAX_NEW_TOKENS: Maximum number of tokens for the Gemini response (default: 2048).

   • REDIS_URL: The URL of your Redis server (default: redis://localhost:6379).

   • FLASK_ENV, FLASK_APP: Optional, related to Flask if used elsewhere, not core to the MCP server/worker operation.

Running the Service

1. Ensure Redis is running. If you installed it locally, you might need to start the Redis server process (e.g., redis-server command, or via a service manager).

2. Start the RQ Worker: Open a terminal, activate your virtual environment (source .venv/bin/activate or similar), and run:

   python -m mcp_waifu_queue.worker

   This command starts the worker process, which will listen for jobs on the Redis queue defined in your .env file. Keep this terminal running.

3. Start the MCP Server: Open another terminal, activate the virtual environment, and run the MCP server using a tool like uvicorn (you might need to install it: pip install uvicorn or uv pip install uvicorn):

   uvicorn mcp_waifu_queue.main:app --reload --port 8000 # Example port

   Replace 8000 with your desired port. The --reload flag is useful for development.

   Alternatively, you can use the start-services.sh script (primarily designed for Linux/macOS environments) which attempts to start Redis (if not running) and the worker in the background:

   # Ensure the script is executable: chmod +x ./scripts/start-services.sh ./scripts/start-services.sh # Then start the MCP server manually as shown above.

MCP API

The server provides the following MCP-compliant endpoints:

Tools

• generate_text

  • Description: Sends a text generation request to the Gemini 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)

Resources

• job://{job_id}

  • Description: Retrieves the status and result of a previously submitted job.

  • URI Parameter: job_id (The ID returned by the generate_text tool).

  • Output: {"status": "...", "result": "..."} (Type: JobStatusResponse)

    • status: The current state of the job (e.g., "queued", "started", "finished", "failed"). RQ uses slightly different terms internally ("started" vs "processing", "finished" vs "completed"). The resource maps these.

    • result: The generated text from Gemini if the job status is "completed", otherwise null. If the job failed, the result might be null or contain error information depending on RQ's handling.

Testing

The project includes tests. Ensure you have installed the test dependencies (pip install -e .[test] or uv pip install -e .[test]).

Run tests using pytest:

Note: Tests might require mocking Redis (fakeredis) and potentially the Gemini API calls depending on their implementation.

Troubleshooting

• Error: : Ensure OPENROUTER_API_KEY is set or ~/.api-openrouter exists with your key on a single line (no whitespace).

• Error: : Ensure GEMINI_API_KEY or GOOGLE_API_KEY is set, or ~/.api-gemini exists with your key on a single line.

• Error during Gemini API call (e.g., AuthenticationError, PermissionDenied): Double-check that the API key in ~/.api-gemini (or the fallback environment variable) is correct and valid. Ensure the API is enabled for your Google Cloud project if applicable.

• Jobs stuck in "queued": Verify that the RQ worker (python -m mcp_waifu_queue.worker) is running in a separate terminal and connected to the same Redis instance specified in .env. Check the worker logs for errors.

• ConnectionRefusedError (Redis): Make sure your Redis server is running and accessible at the REDIS_URL specified in .env.

• MCP Server Connection Issues: Ensure the MCP server (uvicorn ...) is running and you are connecting to the correct host/port.

Contributing

1. Fork the repository.

2. Create a new branch for your feature or bug fix (git checkout -b feature/your-feature-name).

3. Make your changes and commit them (git commit -am 'Add some feature').

4. Push your branch to your forked repository (git push origin feature/your-feature-name).

5. Create a new Pull Request on the original repository.

Please adhere to the project's coding standards and linting rules (ruff).

License

This project is licensed under the MIT-0 License - see the LICENSE file for details.