AI agents call get_user_fills to retrieve information from Liquidiction without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves past trade records for a specified user address. It is a read-only operation with no side effects, no code execution, and no financial transactions. The user address appears to be a query parameter to filter results. Even though it relates to trading data, the tool itself only reads and does not execute trades, move funds, or modify state.
From the tool's definition Tool name 'get_user_fills' and description 'Get trade history for a user address' indicate a query operation that retrieves historical trade data without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access get_user_fills gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Liquidiction, and nothing reaches the server without passing your rules. This is the rule we recommend for get_user_fills:
{
"version": "1",
"default": "deny",
"tools": {
"get_user_fills": {}
}
}get_user_fills 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.
Get trade history for a user address. It is categorised as a Read tool in the Liquidiction MCP Server, which means it retrieves data without modifying state.
Register the Liquidiction MCP server in PolicyLayer and add a rule for get_user_fills: 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 Liquidiction. Nothing to install.
get_user_fills 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 get_user_fills 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 get_user_fills. 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.
get_user_fills is provided by the Liquidiction MCP server (liquidiction/liquidiction-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Liquidiction, 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.
10 Liquidiction tools catalogued and risk-classified — across an index of 43,000+ MCP servers.