AI agents call learning_stats to retrieve information from Srclight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches and returns learning statistics (counts organized by kind over a time dimension). The verb 'Get' and the nature of statistics as read-only summaries confirm this is a pure data retrieval operation with no capability to modify, delete, or execute code. The low severity reflects minimal risk from misuse by an AI agent, as it can only observe historical statistics.
From the tool's definition Tool name 'learning_stats' and description 'Get learning statistics — counts by kind over time' indicate retrieval of aggregated statistical data with no mutation or side effects.
Documented attack patterns abuse exactly the kind of access learning_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Srclight, and nothing reaches the server without passing your rules. This is the rule we recommend for learning_stats:
{
"version": "1",
"default": "deny",
"tools": {
"learning_stats": {}
}
}learning_stats is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get learning statistics — counts by kind over time. It is categorised as a Read tool in the Srclight MCP Server, which means it retrieves data without modifying state.
Register the Srclight MCP server in PolicyLayer and add a rule for learning_stats: 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 Srclight. Nothing to install.
learning_stats 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 learning_stats 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 learning_stats. 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.
learning_stats is provided by the Srclight MCP server (srclight/srclight). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 42 Srclight tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
42 Srclight tools catalogued and risk-classified — across an index of 42,500+ MCP servers.