GoalGorithm MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| predict_matchA | Predict soccer match outcome using xG-based Poisson model. Returns win/draw/loss probabilities, over/under 2.5 goals, both teams to score, and top 3 most likely scores. Args: home_team: Home team name (e.g. "Arsenal") away_team: Away team name (e.g. "Chelsea") league: League slug, name, or ID (default: EPL) |
| list_leaguesA | List all supported soccer leagues with IDs and slugs. |
| get_league_tableA | Get all teams in a league with their xG statistics. Returns teams sorted by attacking strength (xG per 90 minutes). Args: league: League slug, name, or ID (default: EPL) |
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 3 tools
Each tool has a clearly distinct purpose: get_league_table retrieves team statistics, list_leagues provides league metadata, and predict_match forecasts match outcomes. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun naming pattern (get_league_table, list_leagues, predict_match). The verbs are descriptive and appropriate for their actions, and the snake_case style is uniformly applied across all tools.
With only 3 tools, the server feels thin for a soccer analytics domain. While the tools cover key areas (leagues, tables, predictions), additional operations like historical match data or player statistics could enhance completeness, making the count borderline for the apparent scope.
The tools provide a solid foundation for soccer analytics with league listing, table retrieval, and match prediction. However, there are minor gaps, such as missing update or delete operations for leagues or teams, and no tools for deeper statistical analysis or historical data, which agents might need to work around.