There and back again... by ferry or I-5?
summary
A concrete build that uses the Model Context Protocol (MCP) to fetch WA Dept of Transportation ferry schedules, Google Maps drive times and live traffic, and calendar events, then compares options and issues notifications. Stack: Python in Docker with fast MCP, Claude Desktop as the LLM client, and Elastic Search for event storage. Example outputs: a 1h18m drive costs ~$56, a 2h45m ferry trip costs ~$41; system generates expense estimates, actionable route choices, and sends timely alerts.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 1:02Ferry commuting background
- 2:30Commute options overview
- 4:13MCP server for lookups
- 5:17MCP development process
- 9:51MCP technical stack
- 11:39MCP framework history
- 13:28MCP resources overview
- 17:37MCP tools and dynamics
- 20:26Agent prompts guide
- 23:21Fast MCP integration
- 24:29MCP and agentic AI
- 26:12Live MCP demo
- 34:05Elasticsearch integration
- 35:16Q&A
related talks
32mThere and back again... but by I-5 or the ferry?
50mBeyond local tools: Dive into the Model Context Protocol (MCP)
32mMCP for dummies: Feed more context to LLM
30mHello, MCP World!
25mFrom Idea to Integration: An Intro to the Model Context Protocol (MCP)
44mBuilding an MCP Server for Tesla Before Elon Lost the Plot
17mMCP Is Not Good Yet
35mMCP in Action: Real-World Use Cases & Design Patterns