https://github.com/av/tools

Docker image for installing and running tools for LLM agents (MCP, OpenAPI, UVX, NPX, Python)
https://github.com/av/tools

agents containerization docker image llm mcp openapi package tools

Last synced: 17 days ago
JSON representation

Docker image for installing and running tools for LLM agents (MCP, OpenAPI, UVX, NPX, Python)

• Host: GitHub
• URL: https://github.com/av/tools
• Owner: av
• License: mit
• Created: 2025-04-05T08:49:48.000Z (21 days ago)
• Default Branch: main
• Last Pushed: 2025-04-05T10:14:04.000Z (21 days ago)
• Last Synced: 2025-04-05T10:27:00.809Z (21 days ago)
• Topics: agents, containerization, docker, image, llm, mcp, openapi, package, tools
• Language: Dockerfile
• Homepage:
• Size: 21.5 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

        
![./assets/tools.png](./assets/tools.png)

Docker image for installing and running tools for LLM agents (MCP, OpenAPI, UVX, NPX, Python)

### Features

- Python / Node.js runtime - includes `python`, `node`, `uvx`, `npx`

- Includes extra packages for managing MCP/OpenAPI tools and connections

  - [`mcpo`](https://github.com/open-webui/mcpo) - MCP to OpenAPI bridge

  - [`supergateway`](https://github.com/supercorp-ai/supergateway) - MCP STDIO/SSE bridge

  - [`@modelcontextprotocol/inspector`](https://github.com/modelcontextprotocol/inspector) - debugging tool for MCP

- Utils: `curl`, `jq`, `git`

- Easy unified cache at `/app/cache` for all tools

### Usage

```bash

# Launch MCP tools in stdio mode

docker run ghcr.io/av/tools uvx mcp-server-time

# Bridge from MCP to OpenAPI

docker run -p 8000:8000 ghcr.io/av/tools uvx mcpo -- uvx mcp-server-time --local-timezone=America/New_York

# http://0.0.0.0:8000/docs -> see endpoint documentation

# Run MCP inspector

docker run -p 6274:6274 -p 6277:6277 ghcr.io/av/tools npx @modelcontextprotocol/inspector

# Persist the cache volume for quick restarts

# -v cache:/app/cache - named docker volume

# -v /path/to/my/cache:/app/cache - cache on the host

docker run -v cache:/app/cache ghcr.io/av/tools uvx mcp-server-time

```

In docker compose:

```yaml

services:

  time:

    image: ghcr.io/av/tools

    command: uvx mcp-server-time

    volumes:

      - cache:/app/cache

  fetch:

    image: ghcr.io/av/tools

    command: uvx mcpo -- uvx mcp-server-fetch

    ports:

      - 7133:8000

    volumes:

      - cache:/app/cache

```

---

Check out [Harbor](https://github.com/av/harbor) for a complete dockerized LLM environment.