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.
This record as markdown: /tools/com-footdigest-footdigest/get-match-probabilities.md
What get_match_probabilities does on Footdigest
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
match_id | integer | — | Scheduled fixture id. |
away_team | string | — | Away (or second) team name. |
home_team | string | — | Home (or first) team name. |
Parameters from the server's own tool schema.
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 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 signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs get_match_probabilities safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Footdigest, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_match_probabilities, this is the rule to start with:
get_match_probabilities is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Footdigest, apply this rule, and every get_match_probabilities call is checked against it from then on.
Questions about 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. It is categorised as a Read tool in the Footdigest MCP Server, which means it retrieves data without modifying state.
get_match_probabilities accepts 3 parameters: match_id, away_team, home_team. The full parameter table on this page comes from the server's own tool schema.
Register the Footdigest MCP server in PolicyLayer and add a rule for get_match_probabilities: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Footdigest. Nothing to install.
get_match_probabilities is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_match_probabilities rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_match_probabilities. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_match_probabilities is provided by the Footdigest MCP server (https://footdigest.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Footdigest, and thousands of servers like it.
This server
Across the catalogue