# score_prob

Market-implied correct-score probabilities for ONE football match — ONE call. Inverts the de-vigged 1x2 (power de-vig) + totals prices into a bivariate-Poisson (Dixon-Coles) score grid and returns the top-K scorelines with probabilities, the fitted goal rates (lambda_home/lambda_away), and how much probability mass the list covers. The asian-handicap fair price is held out of the fit and reported as ah_ev_check (≈0 means the three markets are internally consistent). This is the market's own distribution, never an InferSports prediction. Football only, one match per call. Args: query: natural-language fixture, e.g. "Mexico vs South Africa" or a single team. sport: optional filter; only "football" is supported by this tool. date: optional UTC date "YYYY-MM-DD" to disambiguate same-name fixtures. top: how many scorelines to return (default 5, max 10).

Agent View of the PolicyLayer registry record for `score_prob`. HTML page: https://policylayer.com/tools/dev-infersports-infersports/score-prob

## Facts

- Tool: `score_prob`
- Server: Infersports (`https://api.infersports.dev/mcp`) — https://policylayer.com/tools/dev-infersports-infersports.md
- Homepage: https://github.com/https://api.infersports.dev/mcp
- Risk category: Read (Low risk)
- Registry record: grade C, identity unverified
- Server auth posture: open
- Server rate-limited: no
- Parameters: 4 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `top` | integer | no |  |
| `date` | object | no |  |
| `query` | string | yes |  |
| `sport` | object | no |  |

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": "score_prob",
    "arguments": {
      "query": "<query>"
    }
  }
}
```

## Why score_prob is rated Low

This tool queries and transforms existing odds/pricing data into derived probability estimates for a single match. It performs statistical analysis (Dixon-Coles Poisson fitting) on market data but neither creates, modifies, executes external operations, nor deletes anything. It is strictly informational retrieval with no side effects, fitting the Read category cleanly.

From the tool's own definition: "Tool description states 'Read-only' server; 'score_prob' inverts existing market prices into probabilities and returns analysis results with no modification of underlying data."

## Use case

AI agents call score_prob to retrieve information from Infersports 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 Infersports:

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

## Other tools on Infersports (16)

- `compare_lines` — Read — https://policylayer.com/tools/dev-infersports-infersports/compare-lines.md
- `compare_prob` — Read — https://policylayer.com/tools/dev-infersports-infersports/compare-prob.md
- `explain_handicap` — Read — https://policylayer.com/tools/dev-infersports-infersports/explain-handicap.md
- `find_arbitrage` — Read — https://policylayer.com/tools/dev-infersports-infersports/find-arbitrage.md
- `find_match` — Read — https://policylayer.com/tools/dev-infersports-infersports/find-match.md
- `find_value` — Read — https://policylayer.com/tools/dev-infersports-infersports/find-value.md
- `get_match_odds` — Read — https://policylayer.com/tools/dev-infersports-infersports/get-match-odds.md
- `get_opening_line` — Read — https://policylayer.com/tools/dev-infersports-infersports/get-opening-line.md
- `get_result` — Read — https://policylayer.com/tools/dev-infersports-infersports/get-result.md
- `get_sharp_line` — Read — https://policylayer.com/tools/dev-infersports-infersports/get-sharp-line.md
- `list_bookmakers` — Read — https://policylayer.com/tools/dev-infersports-infersports/list-bookmakers.md
- `list_events` — Read — https://policylayer.com/tools/dev-infersports-infersports/list-events.md
- `list_results` — Read — https://policylayer.com/tools/dev-infersports-infersports/list-results.md
- `list_today_matches` — Read — https://policylayer.com/tools/dev-infersports-infersports/list-today-matches.md
- `match_info` — Read — https://policylayer.com/tools/dev-infersports-infersports/match-info.md
- `scan_slate` — Read — https://policylayer.com/tools/dev-infersports-infersports/scan-slate.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=dev-infersports-infersports · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/dev-infersports-infersports