piercloud-mcp 0.1.0

A scalable MCP server with clean architecture

Pier Cloud MCP Server

A scalable Model Context Protocol server with clean architecture.

Quick Start

# Setup
poetry install

# Local mode (stdio)
poetry run piercloud-mcp

# Production mode (HTTP/SSE)
poetry run piercloud-mcp --sse --port 8000

Production Deployment

Deploy as HTTP server at https://mcp.piercloud.io:

# Run server
poetry run piercloud-mcp --sse --port 8000

MCP Protocol (Claude, Cline, etc)

{
  "mcpServers": {
    "pier": {
      "url": "https://mcp.piercloud.io/mcp/sse"
    }
  }
}

REST API (ChatGPT, Gemini, any LLM)

# List tools
curl https://mcp.piercloud.io/api/tools

# Execute tool
curl -X POST https://mcp.piercloud.io/api/tools/echo \
  -H "Content-Type: application/json" \
  -d '{"message": "hello", "uppercase": true}'

# OpenAPI spec
curl https://mcp.piercloud.io/openapi.json

Adding Tools

Create a new file in src/pier_mcp/tools/ and register:

from pydantic import BaseModel, Field

class MyToolInput(BaseModel):
    param: str = Field(description="Parameter description")

def register_my_tools(mcp):
    @mcp.tool("my_tool", "Tool description", MyToolInput)
    async def my_tool(args: MyToolInput) -> str:
        return f"Result: {args.param}"

Then import in main.py:

from pier_mcp.tools.my_tools import register_my_tools
register_my_tools(mcp)

Architecture

• server.py - Core MCP server with tool registry
• tools/ - Tool implementations (one file per domain)
• main.py - Entry point and tool registration

Clean, minimal, scalable.