# get_match_probabilities

Footdigest: calibrated home/draw/away probabilities and expected goals for a football matchup, from the backtested Dixon-Coles + Elo engine. Ask by match_id, or by home_team and away_team names for any matchup. Every answer is sourced and timestamped; see get_model_card for the methodology.

Agent View of the PolicyLayer registry record for `get_match_probabilities`. HTML page: https://policylayer.com/tools/com-footdigest-footdigest/get-match-probabilities

## Facts

- Tool: `get_match_probabilities`
- Server: Footdigest (`https://footdigest.com/mcp`) — https://policylayer.com/tools/com-footdigest-footdigest.md
- Homepage: https://github.com/https://footdigest.com/mcp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 3
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `match_id` | integer | no | Scheduled fixture id. |
| `away_team` | string | no | Away (or second) team name. |
| `home_team` | string | no | Home (or first) team name. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_match_probabilities",
    "arguments": {}
  }
}
```

## Why get_match_probabilities is rated Low

This tool performs a straightforward data retrieval operation—it queries football match probability predictions from a pre-trained model. No side effects, modifications, deletions, code execution, or financial transactions are possible. The action is read-only, fitting the 'Read' category of tools that retrieve or query data without side effects.

From the tool's own definition: "Tool retrieves and queries 'calibrated home/draw/away probabilities and expected goals' with no mention of modifying, deleting, or executing operations. The description explicitly states it 'asks by' parameters and returns sourced, timestamped data."

Risk signals: Bulk/mass operation — affects multiple targets

## Use case

AI agents call get_match_probabilities to retrieve information from Footdigest without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Footdigest:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_match_probabilities": {}
  }
}
```

## Other tools on Footdigest (13)

- `simulate` — Execute — https://policylayer.com/tools/com-footdigest-footdigest/simulate.md
- `get_bracket` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-bracket.md
- `get_defining_moments` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-defining-moments.md
- `get_head_to_head` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-head-to-head.md
- `get_match` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-match.md
- `get_match_brief` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-match-brief.md
- `get_model_card` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-model-card.md
- `get_qualification_scenarios` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-qualification-scenarios.md
- `get_schedule` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-schedule.md
- `get_standings` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-standings.md
- `get_suspension_watch` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-suspension-watch.md
- `get_team_availability` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-team-availability.md
- `get_tournament_odds` — Read — https://policylayer.com/tools/com-footdigest-footdigest/get-tournament-odds.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=com-footdigest-footdigest · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/com-footdigest-footdigest