Get detailed explainability for AI projection decisions using SHAP values. Shows which features contributed most to a player
AI agents call explain_recommendation to retrieve information from SportIntel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read operation by querying model explainability data (SHAP values) to show feature contributions. It has no side effects, does not modify data, execute arbitrary code, delete information, or move money. While the parent server involves financial activities (DFS), this specific tool only retrieves explanatory information, making it a Read-category tool with low severity risk.
From the tool's definition Tool name 'explain_recommendation' and description 'Get detailed explainability for AI projection decisions using SHAP values' indicates the tool retrieves and displays analytical reasoning data.
Attacks that exploit this kind of access
Get detailed explainability for AI projection decisions using SHAP values. Shows which features contributed most to a player. It is categorised as a Read tool in the SportIntel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SportIntel MCP Server MCP server in PolicyLayer and add a rule for explain_recommendation: 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 SportIntel MCP Server. Nothing to install.
explain_recommendation 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 explain_recommendation 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 explain_recommendation. 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.
explain_recommendation is provided by the SportIntel MCP Server MCP server (roizenlabs/sportintel-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 →