CONNECT APP

Build with OpenWeather API

OpenWeather provides comprehensive weather data services, including current, forecast, and historical weather information.

Travel

API key

Visit OpenWeather API ↗ Start building

MCP

Give your agent OpenWeather API tools

Every OpenWeather API action is exposed as an MCP tool on Pipedream's remote server. Point a client at it with your end user's ID and Connect resolves that user's OpenWeather API account for each tool call — you store no tokens.

Pipedream Connect

// accessToken: mint a short-lived token with the Connect SDK — see the MCP guide
const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": "{project_id}",
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "openweather_api",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// e.g. run Get Current Weather by Location:
const result = await mcp.callTool({
  name: "openweather_api-get-current-weather-by-location",
  arguments: {
    city: "City",
    stateCode: "State code",
  },
})

# access_token: mint a short-lived token with the Connect SDK — see the MCP guide
headers = {
    "Authorization": f"Bearer {access_token}",
    "x-pd-project-id": "{project_id}",
    "x-pd-environment": "production",
    "x-pd-external-user-id": "{external_user_id}",  # any stable ID for this user in your system
    "x-pd-app-slug": "openweather_api",
}

async with streamablehttp_client("https://remote.mcp.pipedream.net/v3", headers=headers) as (read, write, _):
    async with ClientSession(read, write) as session:
        await session.initialize()
        tools = await session.list_tools()

        # e.g. run Get Current Weather by Location:
        result = await session.call_tool("openweather_api-get-current-weather-by-location", {
            "city": "City",
            "stateCode": "State code",
        })

MCP guide →

API PROXY

Call the OpenWeather API API directly

For an endpoint with no pre-built tool, the Connect proxy forwards your request to the OpenWeather API API with the connected user's credentials attached. You store no tokens and write no refresh logic.

Pipedream Connect

const resp = await pd.proxy.get({
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  accountId: "apn_xxxxxxx",
  url: "https://api.openweathermap.org/data/2.5/weather",
})

// Any allowed OpenWeather API endpoint works here. Pipedream attaches the
// connected account's credentials to the outgoing request.

# The path segment is the target URL, URL-safe base64 encoded:
# https://api.openweathermap.org/data/2.5/weather

curl "https://api.pipedream.com/v1/connect/{project_id}/proxy/aHR0cHM6Ly9hcGkub3BlbndlYXRoZXJtYXAub3JnL2RhdGEvMi41L3dlYXRoZXI?external_user_id={external_user_id}&account_id=apn_xxxxxxx" \
  -H "Authorization: Bearer {access_token}" \
  -H "x-pd-environment: production"

API proxy guide →

SDK

Run OpenWeather API actions from your backend

Connect a user's OpenWeather API account once, then run Get Current Weather by Location on their behalf from your own code — TypeScript, Python, or plain HTTP.

Pipedream Connect

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "openweather_api-get-current-weather-by-location",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    openweather_api: { authProvisionId: "apn_xxxxxxx" },
    city: "City",
    stateCode: "State code",
  },
})

from pipedream import Pipedream

pd = Pipedream(
    client_id="{oauth_client_id}",
    client_secret="{oauth_client_secret}",
    project_id="{project_id}",
    project_environment="production",
)

result = pd.actions.run(
    id="openweather_api-get-current-weather-by-location",
    external_user_id="{external_user_id}",  # any stable ID for this user in your system
    configured_props={
        "openweather_api": {"authProvisionId": "apn_xxxxxxx"},
        "city": "City",
        "stateCode": "State code",
    },
)

curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "openweather_api-get-current-weather-by-location",
    "configured_props": {
      "openweather_api": { "authProvisionId": "apn_xxxxxxx" },
      "city": "City",
      "stateCode": "State code"
    }
  }'