AI agents call get_season 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 or queries season information from an existing database without modifying, deleting, or executing code. It is a read-only data lookup operation with minimal blast radius if misused—at worst, an AI agent could spam queries or retrieve unwanted information, but no irreversible changes or code execution are possible.
From the tool's definition Tool name 'get_season' and server description indicate data retrieval from RGL.gg competitive TF2 database. The function appears to perform a 'reverse lookup' to resolve a SeasonId to season information.
Attacks that exploit this kind of access
Reverse lookup: resolve an internal SeasonId (e.g. the. 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_season: 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_season 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_season 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_season. 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_season 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.
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 →