AI agents call continue_explore to retrieve information from Smithsonian Open Access MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to be part of a read-only exploration interface for the Smithsonian collections. Despite having an empty description, the name 'continue_explore' combined with the server's stated purpose of enabling assistants to 'search, explore, and analyze' collection objects, and the pattern of sibling tools that are all retrieval-focused (get_*, find_*), strongly suggests this tool retrieves or queries data…
From the tool's definition Tool name 'continue_explore' with sibling tools including 'find_and_describe', 'find_on_view_items', 'get_collection_statistics', 'get_object_details' indicates browsing/querying functionality.
Documented attack patterns abuse exactly the kind of access continue_explore gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Smithsonian Open Access MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for continue_explore:
{
"version": "1",
"default": "deny",
"tools": {
"continue_explore": {}
}
}continue_explore 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.
continue_explore. It is categorised as a Read tool in the Smithsonian Open Access MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smithsonian Open Access MCP Server MCP server in PolicyLayer and add a rule for continue_explore: 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 Smithsonian Open Access MCP Server. Nothing to install.
continue_explore 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 continue_explore 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 continue_explore. 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.
continue_explore is provided by the Smithsonian Open Access MCP Server MCP server (molanojustin/smithsonian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Smithsonian Open Access 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.
28 Smithsonian Open Access MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.