1. Click on "Deploy Server".
2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
3. In the chat, type `@` followed by the MCP server name and your instructions, e.g., "`@TableFix MCP` clean this messy CSV into JSON: Name,Age
Alice,30 Bob;25"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a [step-by-step guide with screenshots](https://glama.ai/blog/2025-07-08-how-to-install-and-use-mcp-servers).Submission for the Amazon Developer Hackathon (Alexa+ track) + Open Source mini challenge.
Paste messy delimited text, get back a clean table — exposed as a self-hosted MCP server (MCP spec 2025-11-25, Streamable HTTP) with a simulated Alexa+ conversational layer on top.
Note: Alexa+'s MCP add-on deployment pipeline is currently partner-only, so per the official hackathon rules this project ships the sanctioned alternative: a real, spec-compliant MCP server plus a simulated Alexa+ experience web app that calls the same server. The simulation layer is clearly labeled in the UI.
server.js — local dev MCP server (Express, stateless Streamable HTTP, port 3000)
api/mcp.js — same logic as a Vercel serverless function (/api/mcp)
detect.js — table/delimiter detection (ported from the TableFix project)
sim-web/ — simulated Alexa+ chat UI (calls the MCP server, downloads .xlsx)
vercel.json — rewrites /mcp → /api/mcp
Related MCP server: mcp-csv-server
Tool | Input | Output |
| messy text | delimiter, columns, confidence, scores, suspect rows |
| messy text, | cleaned rows (JSON), delimiter, suspect rows |
npm install
npm start # MCP server on http://localhost:3000
cd sim-web && node serve.js # UI on http://localhost:8080Verify: npm run verify (or see verification.log).
See FRICTION-LOG.md — real integration notes, kept from day one.
MIT — see LICENSE.
This server cannot be deployed
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Open, inspect, filter, edit and convert xlsx and csv files from your AI chat. Processing is local.
Ask questions about a CSV in plain English and get answers, charts and cleaned data back.
Standardize, reshape, and normalize messy data — CSV, Excel, Parquet, S3, databases.