AI agents call get_recent_form to retrieve information from Faceit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates historical match statistics for a player. It performs a read-only query operation with no capability to modify, delete, or execute code. The data returned is publicly available FACEIT player information. The blast radius of misuse is minimal—an agent could only retrieve unwanted performance statistics, which is informational only.
From the tool's definition Tool is named 'get_recent_form' and returns 'aggregated performance stats from a player's most recent matches.' The verb 'return' and context of querying historical performance data indicate data retrieval with no side effects.
Attacks that exploit this kind of access
Return aggregated performance stats from a player's most recent matches. It is categorised as a Read tool in the Faceit MCP Server, which means it retrieves data without modifying state.
Register the Faceit MCP server in PolicyLayer and add a rule for get_recent_form: 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 Faceit. Nothing to install.
get_recent_form 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_recent_form 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_recent_form. 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_recent_form is provided by the Faceit MCP server (tqakdev/faceit-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 →