Low Risk

stock_price_depth

Get order book / price depth (bid/ask levels) for a stock. Args: symbol: Stock ticker symbol (e.g. VNM, FPT, ACB) source: Data source - VCI or KBS (default: VCI)

How to control stock_price_depth ↓

What stock_price_depth does on VNStock Agent MCP Server

AI agents call stock_price_depth to retrieve information from VNStock Agent MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why stock_price_depth needs a policy

This tool queries and retrieves real-time or historical order book data (bid/ask spreads) for Vietnamese stock market symbols. It is a passive data retrieval operation with no side effects, state changes, or ability to execute transactions. Misuse by an AI agent would be limited to accessing or displaying market information that is typically public, posing minimal risk.

From the tool's definition Tool description states 'Get order book / price depth (bid/ask levels) for a stock' — retrieves market data without modification. Arguments are read-only parameters (symbol, source).

Documented attack patterns abuse exactly the kind of access stock_price_depth gives an agent:

How to control stock_price_depth

PolicyLayer is an MCP gateway — it sits between your AI agents and VNStock Agent MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for stock_price_depth:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "stock_price_depth": {}
  }
}

stock_price_depth is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register VNStock Agent MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about stock_price_depth

What does the stock_price_depth tool do? +

Get order book / price depth (bid/ask levels) for a stock. Args: symbol: Stock ticker symbol (e.g. VNM, FPT, ACB) source: Data source - VCI or KBS (default: VCI). It is categorised as a Read tool in the VNStock Agent MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on stock_price_depth? +

Register the VNStock Agent MCP Server MCP server in PolicyLayer and add a rule for stock_price_depth: 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 VNStock Agent MCP Server. Nothing to install.

What risk level is stock_price_depth? +

stock_price_depth is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit stock_price_depth? +

Yes. Add a rate_limit block to the stock_price_depth 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.

How do I block stock_price_depth completely? +

Set action: deny in the PolicyLayer policy for stock_price_depth. 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.

What MCP server provides stock_price_depth? +

stock_price_depth is provided by the VNStock Agent MCP Server MCP server (mrgoonie/vnstock-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every VNStock Agent MCP Server tool call.

Start from VNStock Agent 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.

21 VNStock Agent MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.