> ## Documentation Index
> Fetch the complete documentation index at: https://exa.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Exa API is served at https://api.exa.ai. Authenticate with `Authorization: Bearer $EXA_API_KEY` (or `x-api-key: $EXA_API_KEY`); create keys at https://dashboard.exa.ai/api-keys.
> Prefer the official SDKs, `exa-py` (`pip install exa-py`) and `exa-js` (`npm install exa-js`); both read `EXA_API_KEY` from the environment.
> Tool-using agents can call Exa without writing code through the hosted MCP server at https://mcp.exa.ai/mcp, or install the Exa agent skill with `npx skills add exa-labs/agent-skills` (skill file: https://exa.ai/docs/skill.md).
> The OpenAPI specs at https://exa.ai/docs/exa-spec.yaml and https://exa.ai/docs/team-management-spec.yaml are the source of truth for request and response schemas.

# Sports, Weather & Places

> Find live sports data, weather forecasts, and local places with Exa Search.

Use Exa Search for live sports data, weather forecasts, and local information without integrating a separate API for each one. Ask a natural-language question with the team, place, and time window you care about.

## Write better queries

Name the location or team precisely and include a date whenever the answer changes over time. Add the condition or attribute that matters to your task instead of asking for broad information.

<Tabs>
  <Tab title="Sports" icon="trophy">
    ### Included

    Available sports data:

    * **Scores**: games for a league on a day, including teams, scores, status, start time, and venue
    * **Standings**: current league tables with conference or division splits
    * **Schedules**: past results and upcoming games for a league or team

    Coverage includes the NBA, WNBA, NFL, MLB, NHL, MLS, college basketball and football, major European soccer leagues and UEFA competitions, cricket, F1, UFC, tennis, and golf.

    ### Ask for the league, team, and time

    ```text theme={null}
    NBA scores last night
    ```

    ```text theme={null}
    Lakers schedule this week
    ```

    ### Add the surrounding story

    Ask for the reporting you need alongside the live data.

    ```text theme={null}
    NBA injury reports ahead of tonight's games
    ```
  </Tab>

  <Tab title="Weather" icon="cloud-sun">
    ### Included

    Forecasts include conditions, high and low temperatures, precipitation, wind, humidity, UV index, and sunrise and sunset in the place's local time.

    A query with no date returns today's forecast. Ask for a specific day or range to get one page per day, up to 16 days ahead or 60 days back.

    ### Name the place and day

    ```text theme={null}
    weather in San Francisco tomorrow
    ```

    ### Ask about the condition that affects your plan

    ```text theme={null}
    will it rain in Austin this weekend
    ```

    ### Combine forecasts with reporting

    ```text theme={null}
    hurricane forecast tracks for the Gulf Coast this week
    ```
  </Tab>

  <Tab title="Places" icon="map-pin">
    ### Included

    * Local business profiles, with addresses, hours, amenities, and reviews
    * Venues, attractions, and points of interest
    * Real estate listings and property records
    * Zoning decisions, permits, and planning records

    ### Describe the place like you would ask a local

    Combine the category, neighborhood, and attributes that matter.

    ```text theme={null}
    late-night ramen in the Sunset District with outdoor seating
    ```

    ### Name the record type and geography

    ```text theme={null}
    multifamily zoning variances approved in Denver
    ```

    ### Compare places against practical constraints

    ```text theme={null}
    walkable neighborhoods in Austin with good public schools and under 30 minutes to downtown
    ```
  </Tab>
</Tabs>

## Make a request

All three data types use the same Search endpoint.

<CodeGroup>
  ```python Python theme={null}
  from exa_py import Exa

  exa = Exa()

  results = exa.search(
      "weather in San Francisco tomorrow",
      type="auto",
      num_results=5,
  )
  ```

  ```javascript JavaScript theme={null}
  import Exa from "exa-js";

  const exa = new Exa();

  const results = await exa.search("weather in San Francisco tomorrow", {
    type: "auto",
    numResults: 5,
  });
  ```

  ```bash cURL theme={null}
  curl -s -X POST https://api.exa.ai/search \
    -H "Authorization: Bearer $EXA_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "query": "weather in San Francisco tomorrow",
      "type": "auto",
      "numResults": 5
    }'
  ```
</CodeGroup>

## Get structured data with Exa Agent

For structured data that requires research across multiple sources, use an [Exa Agent task run](/docs/agent/quickstart). Describe the places, teams, dates, criteria, and output fields you need, and Agent returns schema-validated results with citations.

<Card title="Start an Agent task" icon="bot" href="/docs/agent/quickstart" cta="Open Agent guide" arrow="true">
  Compare places, assemble a game-day brief, or combine local details and conditions into structured results.
</Card>