# Underdog AI research assistant

> Build an AI research prompt from a timestamped Underdog board sample with Higher and Lower multipliers, then connect MCP for the full board and history. 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/tools/underdog-ai-assistant

## 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

Free research tool



An AI assistant does not know the current Underdog board unless you give it the data. This tool loads a timestamped sample of current lines with each side’s payout multiplier and builds a prompt that tells ChatGPT, Claude or Gemini to analyze only those rows, quote observation times and never invent lines, multipliers or results. For the full board and recorded line history, connect the Underdog API through MCP.

Choose a board sample Filter by player or team Filter by statFilters apply to the loaded sample of up to 40 lines, not the whole board.

Your evidence prompt

Loading the current board…

## A reproducible research workflow

1. Load a league and check the observation times on the rows.
2. Filter the sample. If the player is missing, query the full board through the API instead of assuming there is no line.
3. Copy the prompt into your assistant and add your question. Ask it to cite the supplied rows and name the evidence it is missing.
4. For history, query line moves, hit rates and game logs for the same player and stat through the API or MCP.

## Connect the full data source

MCP server: `https://underdogapi.com/api/mcp`. Keyless clients can search the docs and read demo data; with a free key your assistant reads the live board, line history and the change feed. Keep the key in your client’s credential settings, never in the chat.

[## Use with ChatGPT Setup steps for the Underdog API in ChatGPT.](https://underdogapi.com/use-with-chatgpt) [## Use with Claude Setup steps for the Underdog API in Claude.](https://underdogapi.com/use-with-claude) [## Use with Gemini Setup steps for the Underdog API in Gemini.](https://underdogapi.com/use-with-gemini) [## Use with Cursor Setup steps for the Underdog API in Cursor.](https://underdogapi.com/use-with-cursor)

Every supported assistant and agent is on the [agents page](https://underdogapi.com/agents).

## Questions

Does an AI assistant automatically know current Underdog lines?

No. Give it a timestamped data source or connect the API. The prompt includes observed rows and tells the assistant to treat them as a sample, not the full board.

Does this generate picks?

No. It builds an evidence prompt for analysis and tells the assistant not to invent lines, multipliers, results or predictions.

Why is the player I want missing from the sample?

The public sample is capped at 40 rows per league. Query the projections endpoint with league, stat or search filters, or the MCP tools, for every matching line.

Can the assistant see line history?

Not from this sample. Connect MCP or call the history and change-feed endpoints to add recorded line moves for a player and stat.

Do I need an account or an API key?

No. The calculator runs in your browser and sends nothing to a server. Copy the link to save or share a calculation. An API key is only for applications that read Underdog lines and multipliers from the API.

## Build on the live board

The Underdog API returns every current Higher and Lower line with each side’s payout multiplier, recorded line history and a change feed. Run this math across the whole board in your own code. Free key with 100 credits a month.

[Get a free API key](https://underdogapi.com/sign-up) [Projections endpoint](https://underdogapi.com/docs#projections)

Last reviewed November 13, 2026. Educational calculations, not picks, betting advice or a promise of profit. Prices move and house rules settle every entry and bet, so check the slip before you play. Independent data service, not affiliated with, endorsed by or sponsored by Underdog Fantasy or Underdog Sports. [Responsible gambling resources](https://www.ncpgambling.org/).

## More free tools

## 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
