AI agents call get_event_matches_keys to retrieve information from Tba without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists match identifiers from The Blue Alliance (a FIRST Robotics competition database). It performs a read-only query operation. The data returned appears to be public competition information. No data is modified, deleted, or executed. The blast radius of misuse is negligible since it only exposes already-public match scheduling data.
From the tool's definition Tool name is 'get_event_matches_keys' and description indicates it 'List[s] match keys at an event' — a retrieval operation that queries data with no side effects.
Attacks that exploit this kind of access
List match keys at an event (strings like. It is categorised as a Read tool in the Tba MCP Server, which means it retrieves data without modifying state.
Register the Tba MCP server in PolicyLayer and add a rule for get_event_matches_keys: 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 Tba. Nothing to install.
get_event_matches_keys 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_event_matches_keys 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_event_matches_keys. 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_event_matches_keys is provided by the Tba MCP server (@withinfocus/tba-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 →