Retrieve draft data. For multi-league associations, specify the league ID.
AI agents call get_draft to retrieve information from StatsPlus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical or current draft information without modifying state, executing code, or triggering external operations. The verb 'Retrieve' and lack of write/execute/destructive indicators place it squarely in the Read category. The blast radius of misuse is minimal—an agent querying draft data cannot harm systems or data integrity.
From the tool's definition Tool name 'get_draft' and description 'Retrieve draft data' indicate a query operation. No mutation, deletion, or execution keywords present.
Attacks that exploit this kind of access
Retrieve draft data. For multi-league associations, specify the league ID. It is categorised as a Read tool in the StatsPlus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the StatsPlus MCP Server MCP server in PolicyLayer and add a rule for get_draft: 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 StatsPlus MCP Server. Nothing to install.
get_draft 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_draft 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_draft. 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_draft is provided by the StatsPlus MCP Server MCP server (joshuarichard/statsplus-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 →