ckan_package_list

THE RISK

Low Risk

Why ckan_package_list needs a policy

This tool queries and returns data about packages/datasets without creating, modifying, or deleting any content. It is a pure read operation that retrieves metadata. No code execution, financial transaction, or destructive action is involved. Severity is low because listing public catalog metadata poses minimal risk even if misused by an agent.

From the tool's definition Tool name includes 'list' and description states 'Get list of all packages (datasets)' — a retrieval operation with no modification or side effects.

Documented attack patterns abuse exactly the kind of access ckan_package_list gives an agent:

POLICY

How to control ckan_package_list

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_package_list:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ckan_package_list": {}
  }
}

ckan_package_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Ckan — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Ckan tools

Read ckan_datastore_search Search records in a dataset Read ckan_group_list Get list of all groups Read ckan_organization_list Get list of all organizations Read ckan_organization_show Get details of a specific organization Read ckan_package_search Search for packages using queries Read ckan_package_show Get details of a specific package/dataset (like dates) Read ckan_resource_show Get details of a specific resource Read ckan_site_read Get site information and statistics

All 11 Ckan tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about ckan_package_list

What does the ckan_package_list tool do? +

Get list of all packages (datasets) in CKAN (unsorted). It is categorised as a Read tool in the Ckan MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ckan_package_list? +

Register the Ckan MCP server in PolicyLayer and add a rule for ckan_package_list: 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.

What risk level is ckan_package_list? +

ckan_package_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ckan_package_list? +

Yes. Add a rate_limit block to the ckan_package_list 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.

How do I block ckan_package_list completely? +

Set action: deny in the PolicyLayer policy for ckan_package_list. 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.

What MCP server provides ckan_package_list? +

ckan_package_list 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.

Enforce policy on every Ckan tool call.

Start from Ckan, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →