SportIntel MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ODDS_API_KEY | Yes | Your API key for the-odds-api.com to access real-time betting odds |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_player_projectionsB | Get AI-powered DFS player projections with confidence scores and SHAP explainability. Returns projected fantasy points, floor/ceiling ranges, and factors driving each projection. |
| optimize_lineupA | Generate optimal DFS lineups using linear programming. Supports cash game and tournament strategies, stacking preferences, and player constraints. Returns multiple lineup variations with risk scores. |
| get_live_oddsB | Get real-time betting odds from multiple sportsbooks. Returns current spreads, totals, moneylines, and player props with line movement history. Identifies best available odds across bookmakers. |
| explain_recommendationA | Get detailed explainability for AI projection decisions using SHAP values. Shows which features contributed most to a player's projection and why the model recommends them. Perfect for understanding the 'why' behind projections. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: explain_recommendation focuses on model explainability, get_live_odds on betting odds, get_player_projections on player forecasts, and optimize_lineup on lineup construction. The descriptions reinforce these unique roles, making tool selection straightforward for an agent.
All tool names follow a consistent verb_noun pattern (explain_recommendation, get_live_odds, get_player_projections, optimize_lineup) with clear, descriptive verbs. There are no deviations in style or convention, ensuring predictable and readable naming throughout the set.
With 4 tools, the count is reasonable for a sports analytics server, covering key areas like projections, odds, explainability, and optimization. It's slightly lean but well-scoped; adding tools for historical data or team-level analysis could enhance completeness without being necessary.
The tools provide solid coverage for DFS and betting workflows, including projection generation, odds retrieval, lineup optimization, and model explainability. Minor gaps exist, such as missing historical performance data or team-level projections, but agents can work effectively with the current surface for core tasks.