Get the access token for the user.
AI agents call get_access_token to retrieve information from Zerodha MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although this is technically a 'Read' operation that retrieves data, the severity is high because access tokens are highly sensitive security credentials that, if exposed to an untrusted AI agent, could enable account takeover and fraudulent trading operations on the Zerodha platform. The tool itself does not execute trades or move money, but obtaining the token is a prerequisite for downstream financial harm.
From the tool's definition Tool name is 'get_access_token' and description states 'Get the access token for the user.' This retrieves an authentication credential without modifying or deleting data.
Attacks that exploit this kind of access
Get the access token for the user. It is categorised as a Read tool in the Zerodha MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zerodha MCP Server MCP server in PolicyLayer and add a rule for get_access_token: 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 Zerodha MCP Server. Nothing to install.
get_access_token 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_access_token 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_access_token. 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_access_token is provided by the Zerodha MCP Server MCP server (jainsourabh2/zerodha-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 →