Skip to main content
Glama
vmridul

my-server

by vmridul

my-server

An MCP server with a weather widget. server.tool({ widget: { dir: "weather" } }) points at src/widgets/weather/ (React). mcpfy-sdk bundles it — no server.widget(), no HTML file, no prompt/resource required.

The weather tool fetches temperature from Open-Meteo on the server. Lookup in the widget calls that tool through the host (callTool) — the iframe does not fetch the API.

If main.tsx later fetches another origin, uncomment widget.csp.connectDomains in src/server.ts. ChatGPT and Claude apply it; Inspector often does not.

Run

Local (starts the MCP server; widgets are bundled on listen — no separate build first):

npm run dev          # default transport: http
npm run dev:stdio
npm run dev:http     # HTTP on port 4000

Production / ChatGPT (iframes cannot use a one-off dev bundle the same way):

npm run build        # mcpfy build && tsc
npm start

Related MCP server: EightyAndSunny

Use it in an MCP host

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["mcpfy", "dev", "--", "--stdio"],
      "cwd": "/absolute/path/to/this-project"
    }
  }
}

Next steps

  • UI: src/widgets/weather/main.tsx (mcpfy-sdk/widget hooks)

  • Tools without UI: omit widget on server.tool()

  • mcpfy docs

A
license - permissive license
Not graded
quality - not tested
C
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Open-Meteo MCP — weather forecast + historical reanalysis + sister APIs

  • MCP server exposing the Backtest360 engine API as tools for AI agents.

  • MCP server for AI dialogue using various LLM models via AceDataCloud

View all MCP Connectors

Latest Blog Posts

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/vmridul/sample-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server