mcpField
M
My Own Assistant

My Own Assistant

Local
github.com/InterpauseAI & Agents1Updated 78w ago

About My Own Assistant

My Own Assistant is a self-hosted assistant project built around Whisper, TTS, and MCP servers. It is for people assembling an assistant with an OpenAI-compatible API; the README describes an ongoing experiment rather than a finished product.

Key features

  1. 01Whisper and TTS integration
  2. 02Support for multiple MCP servers
  3. 03Self-hosted setup
  4. 04OpenAI-compatible API

Use cases

  1. 01Building a self-hosted assistant
  2. 02Experimenting with an MCP-integrated assistant

MCP support

The project is intended to integrate multiple MCP servers into an assistant. The README does not specify which tools or resources it exposes to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

My Own Assistant

Just gonna see if it is now way easier to make your own fully integrated assistant using MCPs. Fully self-hosted too by bringing your own OpenAI compatible API. Just to take advantage of the fact Qwen3-30B-A3B exists.

TODOs

  • Try switching from poetry to uv.

py-api-template

Template for FastAPI-based API server. Features:

  • Supports both CPU/GPU-accelerated setups automatically.
  • Poetry for package management.
  • Ruff for formatting & linting.
  • VSCode debugging tasks.
  • Other QoL packages.

Oh yeah, this template should work with the fancy "Dev Containers: Clone Repository in Container Volume..." feature.

Usage Instructions

  • Replace all instances of py-api-template. Optionally, rename src to a nicer name.
    • Tip: Rename the src folder first for auto-refactoring.

Useful Commands

Ensure the virtual environment is active and poetry install has been run before using the below:

# Launch debugging server, use VSCode's debug task instead by pressing F5.
poe dev
# Run any tests.
poe test
# Build docker image for deployment; will also be tagged as latest.
poe build {insert_version_like_0.1.0}
# Run the latest image locally.
poe prod
# Publish the latest image.
poe publish

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.