Get site information and statistics
AI agents call ckan_site_read to retrieve information from Ckan without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves site-level information and statistics from a CKAN data portal. It performs no data modification, deletion, or code execution. The action is a simple GET operation that returns existing metadata about the portal itself. This is the lowest-risk operation type.
From the tool's definition Tool name contains 'read' and description states 'Get site information and statistics' - purely retrieval of metadata with no modification or execution.
Documented attack patterns abuse exactly the kind of access ckan_site_read gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ckan, and nothing reaches the server without passing your rules. This is the rule we recommend for ckan_site_read:
{
"version": "1",
"default": "deny",
"tools": {
"ckan_site_read": {}
}
} ckan_site_read 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.
Get site information and statistics. It is categorised as a Read tool in the Ckan MCP Server, which means it retrieves data without modifying state.
Register the Ckan MCP server in PolicyLayer and add a rule for ckan_site_read: 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 Ckan. Nothing to install.
ckan_site_read 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 ckan_site_read 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 ckan_site_read. 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.
ckan_site_read is provided by the Ckan MCP server (ondics/ckan-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ckan, 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.
11 Ckan tools catalogued and risk-classified — across an index of 43,000+ MCP servers.