to_pandas

THE RISK

Low Risk

Why to_pandas needs a policy

This tool downloads and transforms existing oceanographic/environmental data into a pandas DataFrame format. It performs no write, delete, execute, or financial operations. The data is retrieved from public ERDDAP servers in read-only fashion. While downloading large datasets could consume resources, the core action is data retrieval with no side effects or irreversible operations.

From the tool's definition Tool description states 'Download data and return as a pandas DataFrame (CSV format)' - a retrieval operation with no modification, deletion, or execution of external code.

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

POLICY

How to control to_pandas

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

policy.json

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

to_pandas 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 ERDDAP MCP Server — 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 ERDDAP MCP Server tools

Read get_dataset_info Get detailed metadata information about a specific dataset Read list_servers List some well-known ERDDAP servers Read search_datasets Search for datasets on an ERDDAP server

All 4 ERDDAP MCP Server 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 to_pandas

What does the to_pandas tool do? +

Download data and return as a pandas DataFrame (CSV format). It is categorised as a Read tool in the ERDDAP MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on to_pandas? +

Register the ERDDAP MCP Server MCP server in PolicyLayer and add a rule for to_pandas: 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 ERDDAP MCP Server. Nothing to install.

What risk level is to_pandas? +

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

Can I rate-limit to_pandas? +

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

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

to_pandas is provided by the ERDDAP MCP Server MCP server (robertdcurrier/erddap2mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every ERDDAP MCP Server tool call.

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

CHECK YOUR STACK →