AI agents call get_districts 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 public information about FIRST Robotics Competition districts for a given year. It performs no modifications, deletions, or external operations—purely data retrieval. The context (Blue Alliance, FRC data) confirms it queries a public sports database. Severity is low as misuse would only retrieve existing public information with no adverse impact.
From the tool's definition Tool name 'get_districts' and description 'List every active FRC district for a given season year' indicate a retrieval/query operation with no side effects.
Attacks that exploit this kind of access
List every active FRC district for a given season year (FIRST in Michigan. 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_districts: 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_districts 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_districts 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_districts. 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_districts 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 →