AI agents invoke run_pandas_code_tool to trigger actions in Pandas-MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Execution of arbitrary pandas code can modify data structures, perform destructive operations (e.g., df.drop(), df.drop_duplicates()), access sensitive data, or consume significant computational resources. Although the server claims to enable 'safe' execution, the tool itself permits running code whose effects depend entirely on the argument supplied.
From the tool's definition Tool name 'run_pandas_code_tool' indicates execution of arbitrary pandas code. Server description states it 'execute[s] pandas code' and the presence of sibling tools for data interpretation and visualization confirms this is a code execution tool, not a…
Documented attack patterns abuse exactly the kind of access run_pandas_code_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pandas-MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_pandas_code_tool:
{
"version": "1",
"default": "deny",
"tools": {
"run_pandas_code_tool": {
"limits": [
{
"counter": "run_pandas_code_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_pandas_code_tool stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
run_pandas_code_tool. It is categorised as a Execute tool in the Pandas-MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pandas-MCP Server MCP server in PolicyLayer and add a rule for run_pandas_code_tool: 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 Pandas-MCP Server. Nothing to install.
run_pandas_code_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_pandas_code_tool 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 run_pandas_code_tool. 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.
run_pandas_code_tool is provided by the Pandas-MCP Server MCP server (marlonluo2018/pandas-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pandas-MCP Server, 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 Pandas-MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.