AI agents call validate_catalog to retrieve information from Now Sdk Ext without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to perform validation logic on a catalog item, which is a query or assessment operation with no permanent state changes. While the ServiceNow server context suggests potential for higher-risk operations, this specific tool's name and description indicate a read-only validation check.
From the tool's definition Tool name 'validate_catalog' and description 'Validate a catalog item' indicate a validation/checking operation without modification or deletion. No evidence of side effects, data changes, or external execution.
Documented attack patterns abuse exactly the kind of access validate_catalog gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Now Sdk Ext, and nothing reaches the server without passing your rules. This is the rule we recommend for validate_catalog:
{
"version": "1",
"default": "deny",
"tools": {
"validate_catalog": {}
}
}validate_catalog 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 a catalog item. It is categorised as a Read tool in the Now Sdk Ext MCP Server, which means it retrieves data without modifying state.
Register the Now Sdk Ext MCP server in PolicyLayer and add a rule for validate_catalog: 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 Now Sdk Ext. Nothing to install.
validate_catalog 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_catalog 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_catalog. 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_catalog is provided by the Now Sdk Ext MCP server (sonisoft-cnanda/now-sdk-ext-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Now Sdk Ext, 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.
86 Now Sdk Ext tools catalogued and risk-classified — across an index of 43,000+ MCP servers.