Get order book / DOM (Depth of Market) data from the chart
AI agents call depth_get to retrieve information from TradingView MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves market depth information (order book data) from TradingView's chart interface. It queries existing data with no side effects, no execution, no modifications, and no destructive or financial actions. The user is simply viewing market microstructure information to inform trading decisions, not executing trades or modifying any state.
From the tool's definition Tool name is 'depth_get' and description states 'Get order book / DOM (Depth of Market) data from the chart' — the verb 'Get' and the read-only nature of retrieving market data without modification.
Attacks that exploit this kind of access
Get order book / DOM (Depth of Market) data from the chart. It is categorised as a Read tool in the TradingView MCP MCP Server, which means it retrieves data without modifying state.
Register the TradingView MCP server in PolicyLayer and add a rule for depth_get: 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 MCP. Nothing to install.
depth_get 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 depth_get 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 depth_get. 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.
depth_get is provided by the TradingView MCP server (ulianbass/tradingview-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 →