# Start with five real rows.

> Download a safe five-row Postman collection, runnable Python and Node.js clients, and connect your agent to the Underdog MCP endpoint. Underdog API (https://underdogapi.com) is an independent Underdog Fantasy pick'em data API: Higher/Lower lines with separate payout multipliers per side, line history, changes and graded results as JSON, CSV, MCP and streams.

Canonical page: https://underdogapi.com/developers/starter-kit

## Free offer

**Free API key, no card: 100 credits a month** on the live board, every league, separate Higher/Lower prices, and the last 24 hours of line history. Sign up: https://underdogapi.com/sign-up?ref=ai-claudebot

## Quickstart

1. Get a free key at https://underdogapi.com/sign-up?ref=ai-claudebot (no card), or let your agent request one: `POST https://underdogapi.com/api/v1/agent/signup` with `data_wanted` and `use_case`, then show your user the returned approval_url.
2. Export it: `export UNDERDOG_API_KEY=ud_...`
3. First call with curl:

```bash
curl --fail-with-body 'https://underdogapi.com/api/v1/projections?league=NBA&view=compact&limit=5' \
  -H "Authorization: Bearer $UNDERDOG_API_KEY" \
  -H 'X-User-Request: NBA dashboard integration check'
```

4. Same call in Python:

```python
import os, requests

r = requests.get(
    "https://underdogapi.com/api/v1/projections",
    params={"league": "NBA", "view": "compact", "limit": 5},
    headers={"Authorization": f"Bearer {os.environ['UNDERDOG_API_KEY']}"},
)
r.raise_for_status()
for line in r.json()["data"]:
    print(line["player"]["name"], line["market"]["stat"], line["line"])
```

## Use it from Claude (MCP)

Claude Code, one command:

```bash
claude mcp add --transport http underdog https://underdogapi.com/api/mcp --header "Authorization: Bearer $UNDERDOG_API_KEY"
```

Or add this server to your Claude MCP configuration (the key stays in the environment):

```json
{
  "mcpServers": {
    "underdog": {
      "type": "http",
      "url": "https://underdogapi.com/api/mcp",
      "headers": {
        "Authorization": "Bearer ${UNDERDOG_API_KEY}"
      }
    }
  }
}
```

Guide: https://underdogapi.com/use-with-claude

## Pricing

| Plan | Price | Credits / month | Notes |
| --- | --- | --- | --- |
| Free | $0 | 100 | No card. Live feed 5 minutes behind; last 24 hours of line history |
| Developer | $49/month | 10,000 | For models that need full training pages and loaded game-log seasons. Live feed, no added plan delay |
| Production | $149/month | 50,000 | For apps with real users and push delivery. Everything in Developer, signed webhooks for every change |
| Scale | $499/month | 250,000 | For apps whose traffic has outgrown Production. Everything in Production, 15 live-feed connections at once |

Full pricing: https://underdogapi.com/pricing

## On this page

Import. Inspect. Run one request.



Test live props, priced comparisons and recorded history with a small request before wiring up your application.

## Download the Postman collection

[Download collection](https://underdogapi.com/postman/underdog-starter.postman_collection.json) [Download environment template](https://underdogapi.com/postman/underdog-starter.postman_environment.json)

1. Import both files into a current Postman desktop app. The environment starts with an empty key and `ALLOW_LIVE_REQUESTS=false`. No request runs on import.
2. [Create an account](https://underdogapi.com/sign-up), finish setup and copy your saved key from [API keys](https://underdogapi.com/dashboard/keys). Set `UNDERDOG_API_KEY` only in your private local environment; do not publish an environment containing a real key.
3. Set `TASK_CONTEXT` to a short, non-sensitive description of your current task. It is sent as `X-User-Request` and retained for 35 days. Leave out private prompts and personal information.
4. Review a single request, set `ALLOW_LIVE_REQUESTS=true`, then press Send. Start with coverage and the credit policy. Set the flag back to false when finished.
5. For result records, supply `RESULTS_DATE`, a US Eastern game date. For a historical board, supply `AS_OF`, an explicit recorded timestamp with timezone. Both start empty and their requests stay skipped until configured.

The collection contains GET requests for coverage, multi-league projections, priced comparisons, results, historical boards and credit costs. Data requests use `limit=5`. There is no automatic pagination, polling, retry loop, purchase or checkout action. Redirect following is disabled. Use a current Postman runtime that supports `pm.execution.skipRequest()`; review imported scripts before running them.

Live reads may consume your account allowance. Five rows are a small response, not a promise that every endpoint costs the same. Inspect `X-Usage-Unit`, `X-Credits-Cost` and `X-Credits-Remaining`, and use the [credit calculator](https://underdogapi.com/credits). A plan gate or empty result stays visible.

## Download the standalone examples

[Download the source bundle](https://underdogapi.com/examples/underdog-api-examples.zip) · [Python quickstart](https://underdogapi.com/examples/underdog-quickstart.py) · [Node.js quickstart](https://underdogapi.com/examples/underdog-quickstart.mjs) · [Jupyter notebook](https://underdogapi.com/examples/underdog-quickstart.ipynb)

Maintained by Stunning Couches LLC and published on our own domain. The bundle includes a README and MIT license for example code, with no credentials or saved notebook output. Data access remains subject to the service terms. Quickstarts default to five rows and one request; without a key they explicitly use fictional demo records.

## Choose a runnable workflow

| Build | Start here | Downloads |
| --- | --- | --- |
| NBA, NFL and NHL comparison feed | [Matching, paging and conditional requests](https://underdogapi.com/docs/league-workflows) | [OpenAPI contract](https://underdogapi.com/openapi.json) |
| Daily NBA stats and graded-line archive | [Date replay, corrections and SQLite upserts](https://underdogapi.com/docs/daily-archive) | [Python archive client](https://underdogapi.com/examples/daily-nba-archive.py) |
| A chronological player-stat baseline | [Model tutorial and evaluation limits](https://underdogapi.com/build-an-nba-prop-model) | [Python model baseline](https://underdogapi.com/examples/nba-player-prop-model.py) |
| League-specific live board | [NBA, NFL, NHL and supported league workflows](https://underdogapi.com/docs/league-workflows) | [OpenAPI contract](https://underdogapi.com/openapi.json) |

Each client has its own request budget and access requirements; review its guide before scheduling it. Preserve source timestamps, grading status, tier, period and unknown values. Older game logs are not proof that Underdog offered a historical line.

## Connect an agent over MCP

The hosted endpoint uses Streamable HTTP in its stateless JSON form. Public search and fetch are available without a key; authenticated data tools use the same account-issued bearer key as REST. Data tool calls take a short non-sensitive `user_request` argument describing the current task.

Endpoint and authenticated data header

```
https://underdogapi.com/api/mcp
Authorization: Bearer YOUR_API_KEY
```

Use the setup instructions for [Claude](https://underdogapi.com/use-with-claude), [Gemini](https://underdogapi.com/use-with-gemini), [Lovable](https://underdogapi.com/use-with-lovable) or [ChatGPT](https://underdogapi.com/use-with-chatgpt). Client capabilities differ; use REST from your application backend and keep keys out of browser bundles. A registry listing is not required to connect to the endpoint.

## Check coverage before promising a feature

The [recorded coverage page](https://underdogapi.com/history-coverage) has its [JSON evidence](https://underdogapi.com/history-coverage.json). It separates recorded line history from box-score history and distinguishes full coverage from a partial recovered snapshot.

For provider evaluation, read the [provider comparisons](https://underdogapi.com/compare) alongside the current [endpoint reference](https://underdogapi.com/docs). This is an independent data service, not an official Underdog API.

[Try **Run a bounded request**](https://underdogapi.com/dashboard/playground) [Evidence **Read the coverage report**](https://underdogapi.com/history-coverage) [Reference **Explore endpoint contracts**](https://underdogapi.com/docs)

## FAQ

### Is there a free Underdog API?

Yes. The Free plan is a real API key on the live board, not a sample: 100 credits a month, every league, separate Higher/Lower prices and the last 24 hours of line history. No card is needed.

### Is this the official Underdog Fantasy API?

No. Underdog API is an independent data service. It is not affiliated with, endorsed by or sponsored by Underdog Fantasy or Underdog Sports.

### What data does it return?

Underdog Higher/Lower lines with separate payout multipliers and availability for each side, stable market ids through line moves, alternate rungs, recorded line history, changes, graded results and coverage/status endpoints.

### How do I use it from Claude or another AI agent?

Connect the MCP server at https://underdogapi.com/api/mcp with a bearer key, or call the REST API. Agents can request a key for their user with POST /api/v1/agent/signup.

### How much does it cost after the free tier?

Developer is $49/month for 10,000 credits, Production $149/month for 50,000, Scale $499/month for 250,000. Errors and unchanged 304 responses cost zero credits.

### How fresh is the data?

Each row carries its observation time. Check /api/v1/status and /api/v1/coverage before relying on a sport or window; missing collection is reported as unavailable, never filled in.

### Does it place entries or give picks?

No. It is data only: no entries, account operations, guaranteed outcomes or betting advice.

---
Independent data service, not affiliated with Underdog Fantasy or Underdog Sports. Docs: https://underdogapi.com/docs · OpenAPI: https://underdogapi.com/openapi.json · llms.txt: https://underdogapi.com/llms.txt
