Accessible Visit

Inspiration

Planning a visit can be difficult when accessibility information is incomplete. Accessible Visit focuses on transparent uncertainty instead of treating missing facts as a guarantee.

What it does

It records venue entry, restroom, seating, and confidence text; saves non-sensitive preferences for step-free access, quiet, and seating; compares needs with facts; and prepares a visit checklist without booking or certifying access. Explicit negatives and unknowns remain non-fit.

How we built it

Python tools persist the entered state in SQLite and run through a local Python MCP server tested via Streamable HTTP (MCP 2025-11-25). A static browser replay, when used, is a JavaScript/localStorage equivalent and is not connected to MCP or Alexa.

Challenges

The core challenge is representing uncertainty honestly: manually entered facts vary in confidence, and unknown restroom or entry information must remain visible for follow-up.

What we learned

A useful planning output can be a question list rather than a yes/no promise.

Accomplishments

The local workflow is verified from venue facts through preferences, assessment, and saved preparation plan, with a fresh Streamable HTTP transcript.

What's next

Add reviewed venue sources, richer preference controls, privacy review, and a real booking or map integration only with verified data and explicit user consent.

This is a local single-user prototype: no cloud or LLM claim, no Alexa/Echo integration, live maps, certification, booking, guarantee, notifications, or medical profile.

Built With

• css3
• fastmcp
• html5
• javascript
• json-schema
• localstorage
• model-context-protocol
• pytest
• python
• sqlite
• streamable-http