AI agents call get_zerodha_holdings to retrieve information from Trade-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account holdings data without executing trades, modifying positions, or moving money. It is a read-only query operation. Severity is low because exposure of holdings data alone does not directly cause financial loss or irreversible damage, though it does reveal sensitive portfolio information.
From the tool's definition Tool name is 'get_zerodha_holdings' and description states 'Get all the holdings in Zerodha' — a retrieval operation with no modification or financial transaction.
Attacks that exploit this kind of access
Get all the holdings in Zerodha. It is categorised as a Read tool in the Trade-MCP MCP Server, which means it retrieves data without modifying state.
Register the Trade- MCP server in PolicyLayer and add a rule for get_zerodha_holdings: 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 Trade-MCP. Nothing to install.
get_zerodha_holdings 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 get_zerodha_holdings 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 get_zerodha_holdings. 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.
get_zerodha_holdings is provided by the Trade- MCP server (samarjyoti496/trade-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 →