This tool is used to login to Zerodha, you will return the login URL to the user, so that they can login to Zerodha, after that you will call set-zerodha-tokens to set the tokens, user will provide you the request token in URL, you will then call another tool for it and pass the request token get...
AI agents use login-to-zerodha to create or update resources in Zerodha MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zerodha MCP Server environment.
This tool performs an authentication flow that writes access tokens and configuration data to disk. It is not purely Read (it saves state), not Execute (no arbitrary code/commands), and not Financial (no money movement). The closest category is Write, as it creates/modifies stored credentials.
From the tool's definition 'login to Zerodha', 'set the tokens', 'save the values in the config file' — the tool initiates an OAuth login flow, retrieves tokens, and persists credentials to a config file
Attacks that exploit this kind of access
This tool is used to login to Zerodha, you will return the login URL to the user, so that they can login to Zerodha, after that you will call set-zerodha-tokens to set the tokens, user will provide you the request token in URL, you will then call another tool for it and pass the request token get the access token and save the values in the config file that function. It is categorised as a Write tool in the Zerodha MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zerodha MCP Server MCP server in PolicyLayer and add a rule for login-to-zerodha: 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.
login-to-zerodha is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the login-to-zerodha 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 login-to-zerodha. 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.
login-to-zerodha is provided by the Zerodha MCP Server MCP server (kshitij-21/mcp-server). 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 →