my_tool
AI agents call my_tool to retrieve information from MCP NIF PT without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without a description, classification relies on context: the server exclusively provides read-only querying of Portuguese company data via a public API. All documented sibling tools retrieve or search data with no side effects. However, the empty description and generic name create substantial uncertainty.
From the tool's definition Tool name 'my_tool' provides no descriptive information. The description is empty. Sibling tools on this server (find_nif_by_name, get_company, search_companies_by_name_and_city, is_active, is_accounting_company) are all Read operations that query the NIF.PT…
Attacks that exploit this kind of access
my_tool. It is categorised as a Read tool in the MCP NIF PT MCP Server, which means it retrieves data without modifying state.
Register the MCP NIF PT MCP server in PolicyLayer and add a rule for my_tool: 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 NIF PT. Nothing to install.
my_tool 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 my_tool 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 my_tool. 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.
my_tool is provided by the MCP NIF PT MCP server (ruicarvalho1/mcp_nif). 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 →