AI agents call paradex_klines to retrieve information from MCP Paradex Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
'klines' refers to candlestick data (K-lines), a read-only market data structure. Given the server's purpose and the absence of order/account modification language in the name, this is clearly a data retrieval operation with no side effects. It poses minimal risk if misused by an AI agent.
From the tool's definition The tool name 'paradex_klines' is standard financial market terminology for candlestick (OHLC) data retrieval.
Documented attack patterns abuse exactly the kind of access paradex_klines gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Paradex Server, and nothing reaches the server without passing your rules. This is the rule we recommend for paradex_klines:
{
"version": "1",
"default": "deny",
"tools": {
"paradex_klines": {}
}
}paradex_klines 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.
paradex_klines. It is categorised as a Read tool in the MCP Paradex Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Paradex Server MCP server in PolicyLayer and add a rule for paradex_klines: 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 MCP Paradex Server. Nothing to install.
paradex_klines 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 paradex_klines 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 paradex_klines. 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.
paradex_klines is provided by the MCP Paradex Server MCP server (sv/mcp-paradex-py). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Paradex 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.
26 MCP Paradex Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.