transcend-mcp-server

transcend-mcp-server

AI-powered route optimization MCP server for heavy vehicles and logistics. Calculate truck-optimized routes, predict traffic congestion with LSTM neural networks, compute toll costs, fuel costs and CO2 emissions, find truck stops and check weather along any European route.

Category
访问服务器

README

Operational MCP layer for European road transport intelligence

License: MIT MCP Python GitHub Release GitHub Stars

A route optimization MCP server that connects AI agents (Claude Desktop, Cline, Continue, Cursor, etc.) to the TRANSCEND logistics intelligence platform — giving LLMs real-time access to truck route optimization, toll costs, weather, parking, traffic blackspots, and fuel station pricing across Spain and Europe.

What problem does it solve? Truck logistics operators waste hours switching between Google Maps (not truck-aware), toll websites, weather apps, and fuel price spreadsheets. This MCP server consolidates 6 real-time logistics data sources into a single AI-callable interface so agents can plan routes, estimate costs, and assess risks in one step.

What makes it different? Unlike generic mapping APIs, TRANSCEND is purpose-built for European truck logistics API needs — it respects ADR (dangerous goods) restrictions, truck height/width/weight limits, provides per-segment toll breakdowns with fuel and CO₂ costs, identifies dangerous blackspot zones, and locates truck-specific parking. It is the only unified MCP interface for European road logistics infrastructure.

What integration does it enable? Any MCP-compatible client can invoke 12 logistics intelligence tools covering route optimization, toll cost estimation, weather conditions, POI parking, traffic blackspot analysis, and fuel station pricing — all from a single conversation with an LLM.

What does "easy integration" mean concretely? pip install the package, set TRANSCEND_API_KEY, and add one JSON config block to Claude Desktop. No microservice orchestration, no multi-API key management, no custom middleware. Your AI assistant gains instant access to professional European logistics document automation and route intelligence.


Why this MCP exists

European truck route planning is fragmented. Google Maps doesn't know truck height restrictions. Toll calculators are per-country. Weather alerts come from a third source. Fuel prices change hourly. Dispatchers manually juggle 5+ tabs to answer a single question like "what's the safest and cheapest route from Madrid to Frankfurt for a 4m-high refrigerated truck?"

This MCP server aggregates six TRANSCEND API microservices (Route, Tolls, Weather, POI, Traffic, Stations) behind a single MCP interface — making European road transport data accessible to AI agents through natural language. It transforms the agent from a chat interface into an operational logistics copilot.


MCP Capabilities

  • 12 MCP tools across 6 logistics modules — organized by domain, not buried in code
  • Truck-aware route optimization with ADR class restrictions, vehicle dimensions, and weight limits
  • Full cost breakdown — tolls + fuel consumption + maintenance + CO₂ emissions per route
  • Real-time weather — current conditions, multi-day forecasts, and active weather alerts along a corridor
  • Truck parking POI search — by coordinates, zip code, or province (with capacity and amenities)
  • Traffic blackspot identification — dangerous road zones along a planned route
  • Fuel station finder — nearby stations, filtered search, and best-price ranking
  • Environment-aware configuration — separate URLs for production vs. dev/release environments
  • HTTP/SSE and stdio transports — works with all MCP clients out of the box
  • Pydantic-validated inputs and outputs — Python 3.10+, httpx async client

Tools

Module Tool Description
🗺️ Route calculate_route Optimized truck route with ADR, height, width, weight constraints
💰 Tolls calculate_route_costs Fuel + tolls + maintenance + CO₂ cost estimation
🌤️ Weather get_current_weather Real-time weather at a location
get_weather_forecast Forecast for a date range
get_weather_alerts Active weather warnings
🅿️ POI find_parking_by_location Truck parking near coordinates
find_parking_by_zipcode Parking by postal code
find_parking_by_province Parking by province
🛑 Traffic get_blackspots_path Dangerous zones along a route
Stations find_stations_nearby Fuel stations near coordinates
search_stations Filter stations by fuel type, text search
get_station_best_prices Best fuel prices near a location

Directory structure

transcend-mcp-server/
├── pyproject.toml                  # Python 3.10+, dependencies: mcp, httpx, pydantic
├── src/transcend_mcp/
│   ├── server.py                   # FastMCP server bootstrap (stdio / HTTP/SSE)
│   ├── client.py                   # Multi-service HTTP client (6 backend APIs)
│   ├── config.py                   # Environment-aware URL resolution (prod / release-dev)
│   ├── tools.py                    # 12 MCP tool definitions with pydantic schemas
│   ├── __init__.py                 # Package init
│   └── __main__.py                 # Entry point for `python -m transcend_mcp`
└── tests/
    └── test_client.py              # Integration tests for client.py

Quick Start

git clone https://github.com/cargoffer/transcend-mcp-server.git
cd transcend-mcp-server
pip install -e .
export TRANSCEND_API_KEY="your-api-key"
python -m transcend_mcp

By default runs on stdio (MCP transport). Set MCP_HOST / MCP_PORT for HTTP/SSE mode.


Installation

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "transcend": {
      "command": "python",
      "args": ["-m", "transcend_mcp"],
      "env": {
        "TRANSCEND_API_KEY": "your-api-key",
        "TRANSCEND_ENV": "production"
      }
    }
  }
}

Cursor

Cursor Settings → Features → MCP Servers → Add New:

Name:   transcend
Type:   command
Command: python -m transcend_mcp
Env:    TRANSCEND_API_KEY=your-api-key, TRANSCEND_ENV=production

Direct HTTP / SSE

export MCP_HOST=0.0.0.0
export MCP_PORT=8100
python -m transcend_mcp

# Then connect SSE at http://localhost:8100/sse

MCP protocol in action

Calculate an optimized truck route:

# With stdio transport, use any MCP client. For HTTP/SSE mode:
# First, connect to SSE endpoint, then send JSON-RPC messages

# Example using the JSON-RPC format over SSE (after establishing connection):
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "calculate_route",
  "params": {
    "origin": "Vigo, Spain",
    "destination": "Barcelona, Spain",
    "dimensions": {
      "height": 4.0,
      "width": 2.55,
      "weight": 40000,
      "adr_class": null
    }
  }
}

Get route costs with real toll data:

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "calculate_route_costs",
  "params": {
    "route_id": "route_abc_123",
    "fuel_consumption": 35,
    "fuel_type": "diesel",
    "include_co2": true
  }
}

Find truck parking along the route:

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "find_parking_by_location",
  "params": {
    "latitude": 41.6488,
    "longitude": -0.8891,
    "radius_km": 10
  }
}

Example Prompts for AI Agents

"Calculate an optimized truck route from Vigo to Barcelona. The truck is 4m high, 2.55m wide, 40 tons. Include blackspot warnings."

"What's the total cost of a 15-ton load from Madrid to Valencia with average fuel consumption of 35L/100km using diesel?"

"Find truck parking near Plaza España in Zaragoza."

"What fuel stations are near the A-2 highway at Guadalajara? Show me the best prices."

"Are there any dangerous zones on the route from Seville to Málaga?"

"What's the weather forecast along the A-3 from Madrid to Valencia for tomorrow? Any alerts?"


Configuration

Environment Variables

Variable Required Default Description
TRANSCEND_API_KEY Your TRANSCEND API key
TRANSCEND_ENV production production or release-dev
LOG_LEVEL INFO Logging verbosity
MCP_HOST localhost HTTP/SSE bind address
MCP_PORT 8100 HTTP/SSE port

Production Microservice URLs

Module Prod URL
Route https://api.transcend.es/route
Tolls https://back.transcend.cargoffer.com/tolls
Weather https://back.transcend.cargoffer.com/weather/api
POI https://back.transcend.cargoffer.com/poi
Traffic https://traffic.transcend.cargoffer.com
Stations https://back.transcend.cargoffer.com/stations

Development

pip install -e ".[dev]"
pytest
ruff check src/
ruff format src/

Semantic tags

route optimization MCP truck logistics API MCP server Model Context Protocol European road transport logistics document automation TRANSCEND truck routing toll calculator fuel prices truck parking weather alerts traffic blackspots ADR restrictions CO2 emissions AI agents LLM tools supply chain Spain logistics Cargoffer easy MCP integration


License

MIT — see LICENSE file for details.


Links

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选