Create a new site (mandatory geographic scope). Only name is required; name must be unique.
AI agents use create_site to create or update resources in API-Central — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your API-Central environment.
This tool creates new data (a site entity) in the network management system, which is reversible (sites can typically be deleted or modified). It does not execute arbitrary commands, delete data irreversibly, move money, or trigger external operations with unpredictable effects. The impact is scoped to a single new site configuration.
From the tool's definition Tool name is 'create_site' and description states 'Create a new site' with requirement that 'name must be unique', indicating creation of a new configuration entity.
Attacks that exploit this kind of access
Create a new site (mandatory geographic scope). Only name is required; name must be unique. It is categorised as a Write tool in the API-Central MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the API-Central MCP server in PolicyLayer and add a rule for create_site: 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 API-Central. Nothing to install.
create_site is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_site 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 create_site. 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.
create_site is provided by the API-Central MCP server (secure-ssid/centralmcp). 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 →