Low Risk

list_accessible_datasets

list_accessible_datasets

How to control list_accessible_datasets ↓

What list_accessible_datasets does on Physionet

AI agents call list_accessible_datasets to retrieve information from Physionet without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why list_accessible_datasets needs a policy

This tool retrieves or enumerates available datasets without modifying any data. It is a straightforward listing/discovery function with no side effects, fitting the Read category. Severity is low because even if misused, listing datasets poses minimal risk—no data is altered, deleted, or exposed beyond what an authenticated user should already have access to.

From the tool's definition Tool name 'list_accessible_datasets' indicates a retrieval operation. Server context describes 'list accessible datasets' as one of the core query/exploration functions alongside 'view schemas' and 'inspect tables', all read-only data exploration activities.

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

How to control list_accessible_datasets

PolicyLayer is an MCP gateway — it sits between your AI agents and Physionet, and nothing reaches the server without passing your rules. This is the rule we recommend for list_accessible_datasets:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_accessible_datasets": {}
  }
}

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

  1. Create a free account and register Physionet — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about list_accessible_datasets

What does the list_accessible_datasets tool do? +

list_accessible_datasets. It is categorised as a Read tool in the Physionet MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_accessible_datasets? +

Register the Physionet MCP server in PolicyLayer and add a rule for list_accessible_datasets: 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 Physionet. Nothing to install.

What risk level is list_accessible_datasets? +

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

Can I rate-limit list_accessible_datasets? +

Yes. Add a rate_limit block to the list_accessible_datasets 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 list_accessible_datasets completely? +

Set action: deny in the PolicyLayer policy for list_accessible_datasets. 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 list_accessible_datasets? +

list_accessible_datasets is provided by the Physionet MCP server (rafiattrach/physionet-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Physionet tool call.

Start from Physionet, 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.

4 Physionet tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.