search_categories_local
AI agents call search_categories_local to retrieve information from Infobel Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name and the pattern of sibling tools on the Infobel API MCP server, this tool appears to retrieve or query category data at a local level with no modification capability. The 'search_categories' naming convention and API context suggest a read-only lookup operation.
From the tool's definition Tool name 'search_categories_local' with empty description; sibling tools include get_available_countries, get_cities, get_currencies, get_languages—all read-only retrieval operations from a business data API.
Attacks that exploit this kind of access
search_categories_local. It is categorised as a Read tool in the Infobel Api MCP Server, which means it retrieves data without modifying state.
Register the Infobel Api MCP server in PolicyLayer and add a rule for search_categories_local: 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 Infobel Api. Nothing to install.
search_categories_local 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 search_categories_local 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 search_categories_local. 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.
search_categories_local is provided by the Infobel Api MCP server (techinfobel/infobel-getdata-api-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 →