bollinger_scan
AI agents call bollinger_scan to retrieve information from Tradingview without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Bollinger Bands scanning is a read-only technical analysis operation that queries market data and indicators without modifying state, executing commands, or committing financial transactions. While the empty description lowers confidence slightly, the context of sibling read-only analysis tools and the absence of any write, execute, or financial language supports Read classification.
From the tool's definition Tool name 'bollinger_scan' suggests analysis of Bollinger Bands technical indicator; description is empty but sibling tools (bitcoin_market_pulse, coin_analysis, combined_analysis, consecutive_candles_scan) indicate this server provides data retrieval and…
Attacks that exploit this kind of access
bollinger_scan. It is categorised as a Read tool in the Tradingview MCP Server, which means it retrieves data without modifying state.
Register the Tradingview MCP server in PolicyLayer and add a rule for bollinger_scan: 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 Tradingview. Nothing to install.
bollinger_scan 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 bollinger_scan 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 bollinger_scan. 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.
bollinger_scan is provided by the Tradingview MCP server (mrxjeus-cpu/trading-mcp-bot). 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 →