Kitesurf Forecast MCP
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kitesurf Forecast MCPGet the kitesurf forecast for lat 41.39, lon -70.51 for the next 24 hours."
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.
MCP_forecast
Kitesurf Forecast MCP
Minimal MCP server exposing two tools:
spot.forecast{lat, lon, hours?} → Open-Meteo Marine hourly wind & waves (knots, meters)
tide.predictions{station_id, begin_date, end_date, time_zone?, units?} → NOAA CO-OPS tide highs/lows
Deploy (Vercel)
Fork/clone → push to GitHub.
Go to vercel.com → New Project → Import your repo.
Build output is the default (Node on serverless). No env vars required.
On success you get: https://.vercel.app
Related MCP server: surfline-mcp
Test
Browser: open the root URL to see discovery JSON.
cURL example (forecast): curl "https://.vercel.app/api/index.js" # should be handled by routes
Use in MCP host
Claude Desktop mcp.json
{ "mcpServers": { "kitesurf-mcp": { "url": "https://.vercel.app" } } }
Then ask: "Using kitesurf-mcp, call spot.forecast for lat=41.39, lon=-70.51, hours=24".
ChatGPT (MCP beta)
Add a custom MCP server → URL: https://.vercel.app
Notes
Open-Meteo returns wind in knots when
wind_speed_unit=kn.NOAA tides require a station id; find one at tidesandcurrents.noaa.gov.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tzuri120-cloud/MCP_forecast'
If you have feedback or need assistance with the MCP directory API, please join our Discord server