List per-team match contributions across many FIRST Robotics Competition (FRC) matches. Each row is one team's involvement in one match (alliance, pre-match EPA, predicted contribution, outcome). Filter by team (one team's entire match log), year, event, week (0-8), match (a single match key - re...
AI agents call get_team_matches to retrieve information from Statbotics without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
elim | boolean | — | Whether the match is an elimination match. |
team | integer | — | Team number (no prefix), e.g. 86 |
week | integer | — | Week of the competition season. 8 is CMP. |
year | integer | — | Four-digit year (2002 onwards) |
event | string | — | Event key, e.g. 2024flor |
limit | integer | — | Maximum number of results to return (1-1000). Default is 1000. |
match | string | — | Match key, e.g. 2024flor_qm20 |
metric | string | — | How to sort the returned values. Any column in the table is valid. |
offset | integer | — | Offset from the first result to return. |
ascending | boolean | — | Whether to sort in ascending order. Default is ascending. |
Parameters from the server's own tool schema.
This tool retrieves historical match data from the Statbotics database without modifying, deleting, or executing operations. It provides read-only access to FIRST Robotics Competition match statistics and team performance metrics. No side effects, state changes, or external operations are triggered. The low severity reflects that misuse would only expose publicly available sports competition data.
From the tool's definition Tool name is 'get_team_matches' and description explicitly states 'List per-team match contributions' with filter, sort, and pagination parameters. The description indicates querying and retrieving data for scouting timelines and comparisons.
Risk signalsHigh parameter count (10 properties)
Attacks that exploit this kind of access
List per-team match contributions across many FIRST Robotics Competition (FRC) matches. Each row is one team's involvement in one match (alliance, pre-match EPA, predicted contribution, outcome). Filter by team (one team's entire match log), year, event, week (0-8), match (a single match key - returns one row per team in that match), and elim (true for elimination matches only). Sort with metric/ascending and paginate with limit/offset. Use this to build a scouting timeline ("every match team 254 played in 2024 with their EPA contribution"), compare alliance partners, or compute per-team averages over a range of matches. It is categorised as a Read tool in the Statbotics MCP Server, which means it retrieves data without modifying state.
get_team_matches accepts 10 parameters: elim, team, week, year, event, limit, match, metric, offset, ascending. The full parameter table on this page comes from the server's own tool schema.
Register the Statbotics MCP server in PolicyLayer and add a rule for get_team_matches: 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 Statbotics. Nothing to install.
get_team_matches 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_team_matches 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_team_matches. 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_team_matches is provided by the Statbotics MCP server (@withinfocus/statbotics-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →