A public tool that doesn't require authentication. Args: query: The query to process Returns: dict with query results
AI agents call public_tool_name to retrieve information from MaverickMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the MaverickMCP server context (stock analysis and financial data), this public tool appears to be a read-only query interface for retrieving financial data or analysis results. The lack of any language indicating side effects (create, update, delete, execute, transfer) and the absence of authentication requirements suggest minimal risk.
From the tool's definition Tool description indicates it 'processes queries' and 'returns query results' with no mention of data modification, deletion, or financial transactions. The vague 'query' parameter and generic return type suggest read-only data retrieval.
Documented attack patterns abuse exactly the kind of access public_tool_name gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MaverickMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for public_tool_name:
{
"version": "1",
"default": "deny",
"tools": {
"public_tool_name": {}
}
}public_tool_name 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.
A public tool that doesn't require authentication. Args: query: The query to process Returns: dict with query results. It is categorised as a Read tool in the MaverickMCP MCP Server, which means it retrieves data without modifying state.
Register the Maverick MCP server in PolicyLayer and add a rule for public_tool_name: 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 MaverickMCP. Nothing to install.
public_tool_name 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 public_tool_name 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 public_tool_name. 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.
public_tool_name is provided by the Maverick MCP server (wshobson/maverick-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 54 MaverickMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
54 MaverickMCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.