AI agents call get_match to retrieve information from Rgl without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical match information from a competitive TF2 database. It has no side effects, cannot modify data, and presents no risk of data loss or unauthorized state changes. The blast radius of misuse is minimal—an agent could retrieve match data but cannot alter records, delete information, or trigger external actions. This is a straightforward Read operation.
From the tool's definition Tool description states 'Fetch a single match' with retrieval of metadata (teams, maps, scores, winner). No mutation, deletion, or code execution capability.
Attacks that exploit this kind of access
Fetch a single match by MatchId (teams, maps, scores, winner). It is categorised as a Read tool in the Rgl MCP Server, which means it retrieves data without modifying state.
Register the Rgl MCP server in PolicyLayer and add a rule for get_match: 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 Rgl. Nothing to install.
get_match 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 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. 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 is provided by the Rgl MCP server (rglgg/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_match is one line of Rgl's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →