AI agents call get_company_by_chid to retrieve information from Zefix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries public Swiss company registry data and returns information without modifying, deleting, or executing anything. Retrieving publicly available company information poses minimal security risk—an AI agent cannot cause harm by fetching read-only data from an official register. Classification as Read with low severity is appropriate.
From the tool's definition Tool 'get_company_by_chid' retrieves detailed information about Swiss companies from the Zefix register. The description uses 'Get', which is a pure retrieval operation. The server description emphasizes 'Search and retrieve' data.
Attacks that exploit this kind of access
Get detailed information about a Swiss company by its CH-ID. It is categorised as a Read tool in the Zefix MCP Server, which means it retrieves data without modifying state.
Register the Zefix MCP server in PolicyLayer and add a rule for get_company_by_chid: 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 Zefix. Nothing to install.
get_company_by_chid 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_company_by_chid 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_company_by_chid. 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_company_by_chid is provided by the Zefix MCP server (johnphilipp/mcp-server-zefix). 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 →