AI agents call pine_categories to retrieve information from Pine Script MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to retrieve or enumerate categories of Pine Script functions or documentation—a read-only operation with no side effects, data modification, or execution of arbitrary code. Even if it discovers categories for filtering purposes, it remains a lookup operation. Severity is low because misuse would only retrieve information, not execute trades or modify trading logic.
From the tool's definition Tool name 'pine_categories' and context of sibling tools (pine_examples, pine_guide, pine_reference, pine_search) all indicate documentation lookup and discovery functions.
Documented attack patterns abuse exactly the kind of access pine_categories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pine Script MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for pine_categories:
{
"version": "1",
"default": "deny",
"tools": {
"pine_categories": {}
}
}pine_categories 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.
Discover what. It is categorised as a Read tool in the Pine Script MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pine Script MCP Server MCP server in PolicyLayer and add a rule for pine_categories: 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 Pine Script MCP Server. Nothing to install.
pine_categories 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 pine_categories 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 pine_categories. 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.
pine_categories is provided by the Pine Script MCP Server MCP server (traderspost/pine-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pine Script MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Pine Script MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.