ShipSmart-MCP

ShipSmart-MCP

A standalone MCP server providing shipping tools like address validation and rate previews through a centralized HTTP interface. It serves as the single source of truth for shipping tool behavior across the ShipSmart platform.

Category
Visit Server

README

ShipSmart-MCP

Standalone MCP (Model Context Protocol) server exposing ShipSmart's shipping tools (validate_address, get_quote_preview, …) over a small HTTP contract.

It is the single source of truth for tool behavior across the platform. Both ShipSmart-API (Python / FastAPI — RAG & LLMs) and ShipSmart-Orchestrator (Java / Spring Boot — upcoming AI features) call this server instead of implementing tools in-process.


HTTP contract

Method Path Purpose
GET / Service discovery (name, version, tool count, endpoints).
GET /health Liveness probe used by Render.
POST /tools/list Return schemas for all registered tools.
POST /tools/call Execute a tool by name with the provided arguments.

Wire-compatible with the MCP tools/list and tools/call semantics: each call returns { success, content: [...], error? }, where content is a list of {type, text} blocks suitable for LLM consumption.

Auth

If MCP_API_KEY is set on the server, every POST /tools/* request must send the matching value in X-MCP-Api-Key. If MCP_API_KEY is empty, auth is disabled (local dev only).


Tools

Name Description
validate_address Validate + normalize a shipping address through the configured carrier.
get_quote_preview Non-binding rate preview for a package. Final rates come from the Java API.

Tools delegate to pluggable ShippingProvider implementations (mock, ups, fedex, dhl, usps) selected by SHIPPING_PROVIDER. Adding a tool is a matter of dropping a new class into app/tools/ and registering it in app/main.py.


Running locally

cp .env.example .env
# fill in credentials if you want real carrier integration; default is SHIPPING_PROVIDER=mock
uv sync
uv run uvicorn app.main:app --reload --host 0.0.0.0 --port 8001

Smoke test:

curl -s http://localhost:8001/health
curl -s -X POST http://localhost:8001/tools/list
curl -s -X POST http://localhost:8001/tools/call \
  -H 'Content-Type: application/json' \
  -d '{
        "name": "validate_address",
        "arguments": {
          "street": "123 Main St",
          "city":   "San Francisco",
          "state":  "CA",
          "zip_code": "94105"
        }
      }'

Tests

uv run pytest

Consumers

  • ShipSmart-API (Python/FastAPI): points SHIPSMART_MCP_URL at the deployed server and calls /tools/list + /tools/call from its orchestration and advisor services.
  • ShipSmart-Orchestrator (Java/Spring Boot): will call the same HTTP contract from its upcoming AI-assist flows. No tool logic lives in the Java codebase.

This keeps the tool layer centralized — add a tool once, every service gets it.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured