FantasyPros MCP Server
# FantasyPros MCP Server
[](https://smithery.ai/server/@DynamicEndpoints/fantasy-pros-mcp)
An MCP server that provides access to the FantasyPros API for sports data, news, rankings, and projections.
## Setup
### Installing via Smithery
To install fantasy-pros-mcp for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@DynamicEndpoints/fantasy-pros-mcp):
```bash
npx -y @smithery/cli install @DynamicEndpoints/fantasy-pros-mcp --client claude
```
### Manual Installation
1. Get a FantasyPros API key by emailing them
2. Create a `.env` file and add your API key:
```
FANTASYPROS_API_KEY=your_api_key_here
```
3. Install dependencies:
```bash
npm install
```
4. Build the server:
```bash
npm run build
```
## Available Tools
### get_sport_news
Get news for a specific sport (NFL, MLB, NBA, NHL)
- Parameters:
- sport: Sport to get news for ('nfl', 'mlb', 'nba', 'nhl')
- limit: Number of news items to return (max 25)
- category: Type of news ('injury', 'recap', 'transaction', 'rumor', 'breaking')
### get_players
Get player information for a specific sport
- Parameters:
- sport: Sport to get players for ('nfl', 'mlb', 'nba', 'nhl')
- playerId: Filter by specific player ID (optional)
### get_rankings
Get consensus rankings for a sport
- Parameters:
- sport: Sport to get rankings for ('nfl', 'nba')
- position: Position to filter by (optional)
- scoring: Scoring type for NFL ('STD', 'PPR', 'HALF')
### get_projections
Get player projections for a sport
- Parameters:
- sport: Sport to get projections for ('nfl', 'mlb', 'nba')
- season: Season year
- week: Week number (for NFL)
- position: Position to filter by (optional)TDQS
Scored across 5 tools
Most tools have distinct purposes targeting different data types (news, players, projections, rankings), but there is some overlap between get_all_news and get_sport_news that could cause confusion about which to use for sport-specific news. The descriptions help clarify, but the boundaries are not perfectly clear.
All tool names follow a consistent verb_noun pattern with 'get_' prefix and snake_case, making them predictable and readable. There are no deviations in naming conventions across the set.
Five tools is reasonable for a fantasy sports data server, covering core data retrieval needs. It might be slightly thin if advanced features like updates or filtering are expected, but it aligns well with a read-only scope.
The tool set provides good read-only coverage for fantasy sports data (news, players, projections, rankings), but there are notable gaps such as no update, delete, or create operations, and no filtering or search tools beyond basic gets. This limits agent workflows to retrieval only.