AI agents call validate_tan to retrieve information from Mcp India Stack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs validation of a Tax Deduction Account Number format, which is a read-only operation that verifies whether input conforms to expected criteria. It has no side effects, does not modify data, execute commands, destroy data, or commit financial transactions.
From the tool's definition The tool name is "validate_tan" and the description states it "Validate[s] TAN (Tax Deduction Account Number) format." This is a format validation operation that queries or checks data against a schema without modifying, executing external operations,…
Documented attack patterns abuse exactly the kind of access validate_tan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp India Stack, and nothing reaches the server without passing your rules. This is the rule we recommend for validate_tan:
{
"version": "1",
"default": "deny",
"tools": {
"validate_tan": {}
}
}validate_tan is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Validate TAN (Tax Deduction Account Number) format. It is categorised as a Read tool in the Mcp India Stack MCP Server, which means it retrieves data without modifying state.
Register the Mcp India Stack MCP server in PolicyLayer and add a rule for validate_tan: 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 Mcp India Stack. Nothing to install.
validate_tan 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 validate_tan 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 validate_tan. 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.
validate_tan is provided by the Mcp India Stack MCP server (rehan1020/mcp-india-stack). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp India Stack, 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.
58 Mcp India Stack tools catalogued and risk-classified — across an index of 43,000+ MCP servers.