START HERE before writing, porting, or backtesting a Pine v6 strategy on
AI agents call list_coverage_topics to retrieve information from PineForge-Codegen without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about coverage topics to guide users before performing backtests. It has no side effects, cannot modify data, execute code, or affect financial instruments. It is purely informational/exploratory in nature, making it a clear Read category with low severity.
From the tool's definition Tool name 'list_coverage_topics' and description 'START HERE before writing, porting, or backtesting' indicates a read-only informational lookup.
Attacks that exploit this kind of access
START HERE before writing, porting, or backtesting a Pine v6 strategy on. It is categorised as a Read tool in the PineForge-Codegen MCP Server, which means it retrieves data without modifying state.
Register the PineForge-Codegen MCP server in PolicyLayer and add a rule for list_coverage_topics: 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 PineForge-Codegen. Nothing to install.
list_coverage_topics 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 list_coverage_topics 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 list_coverage_topics. 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.
list_coverage_topics is provided by the PineForge-Codegen MCP server (oci:ghcr.io/pineforge-4pass/pineforge-codegen-mcp:v0.9.2). 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 →