AI Tools for Developers
About
Your trusted home for discovering MCP tools – seamlessly integrated into Docker
Details
- License
- Apache-2.0
Explore
- Dockerized tools for sandboxed execution
- Markdown as the workflow language
- Conversation loop with automatic error correction
- Multi‑model agents using different LLMs
- Project‑first design with context extraction
- MCP server support with prompt registration
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AI Tools for DevelopersCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install the VSCode extension or use the CLI docker run command. For MCP serve mode, pass the --mcp flag and register prompts using --register <git ref or path>. Set an OpenAI API key (or a dummy value for local models), then run the conversation loop in your editor or terminal.
Agentic AI workflows enabled by Docker containers.
Just Docker. Just Markdown. BYOLLM.
OpenAI API compatiable LLM's already support tool calling. We believe these tools could just be Docker images. Some of the benefits using Docker based on our research are enabling the LLM to:
- take more complex actions
- get more context with fewer tokens
- work across a wider range of environments
- operate in a sandboxed environment
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ai tools for developers": {
"MCP_DOCKER": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"alpine/socat",
"STDIO",
"TCP:host.docker.internal:8811"
]
}
}
}
}McpServers
{
"MCP_DOCKER": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"alpine/socat",
"STDIO",
"TCP:host.docker.internal:8811"
]
}
}Agentic AI workflows enabled by Docker containers.
Just Docker. Just Markdown. BYOLLM.
MCP
Any prompts you write and their tools can now be used as MCP serversUse serve mode with --mcp flag. Then, register prompts via git ref or path with --register <ref>
```sh
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
