aimarket-mcp-packager — MCP server

This repository ships a Model Context Protocol (MCP) server that packages AIMarket capabilities into self-hosted MCP server products (Docker image metadata, MCP manifest, Claude Desktop config).

Transport: stdio (aimarket_mcp_packager/stdio_server.py). Built with the official MCP Python SDK (mcp package, FastMCP).

Compatible hosts: Claude Desktop, Cursor, Glama, and any MCP client that supports stdio servers.

MCP server in this repo

Run locally:

pip install -r requirements-mcp.txt
pip install -e .
python -m aimarket_mcp_packager.stdio_server

Or with Docker (stdio MCP server):

docker build -t aimarket-mcp-packager .
docker run --rm -i aimarket-mcp-packager

MCP tools

The server exposes 3 tools (no MCP resources or prompts):

Example tool call (conceptual):

{
  "name": "package_capability",
  "arguments": {
    "capability_id": "translate.multi@v2",
    "product_id": "prod-001",
    "name": "Lyra",
    "description": "Multilingual translator",
    "input_schema": { "type": "object", "properties": { "text": { "type": "string" } }, "required": ["text"] }
  }
}

input_schema takes a JSON Schema object (a JSON string is also tolerated for backward compatibility). Every tool parameter is documented in the server's tool schema for MCP clients.

MCP resources

This server does not register MCP resources or prompts — only the tools above. Output is JSON text returned from each tool call.

Client configuration

Claude Desktop

{
  "mcpServers": {
    "aimarket-mcp-packager": {
      "command": "python",
      "args": ["/path/to/aimarket-mcp-packager/mcp_stdio_server.py"]
    }
  }
}

Docker variant (see generate_claude_desktop_config tool output):

{
  "mcpServers": {
    "aimarket-mcp-packager": {
      "command": "docker",
      "args": ["run", "--rm", "-i", "aimarket-mcp-packager:latest"]
    }
  }
}

Cursor

Add the same stdio server under Settings → MCP (command + args pointing at aimarket_mcp_packager/stdio_server.py or the Docker image above).

Python library (optional)

The same packaging logic is available as a library and as an AIMarket Hub plugin (PyPI package coming soon — for now pip install -e . from this directory, or use the AIMarket Hub Docker image). Hub HTTP routes are optional; the MCP server runs standalone via aimarket_mcp_packager/stdio_server.py.

from aimarket_mcp_packager.mcp_packager import MCPPackager

packager = MCPPackager()
pkg = packager.package(
    capability_id="translate.multi@v2",
    product_id="prod-001",
    name="Lyra",
    description="Multilingual translator",
    input_schema={"type": "object", "properties": {"text": {"type": "string"}}},
    price_per_call_usd=0.40,
)

print(pkg.docker_image)
print(pkg.mcp_manifest)
print(packager.generate_claude_desktop_config(pkg))

When to use

• Distribute AI capabilities as self-hosted MCP servers (Docker + manifest)
• Generate Claude Desktop / Cursor MCP client configs
• Enterprise on-prem deployment with subscription tiers

Subscription tiers (packaged products)

Documentation

License

MIT · Maintained by AI-Factory