AI agents call search_models to retrieve information from ModelScope MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries models from ModelScope's ecosystem without modifying, deleting, or executing anything. The empty description reduces confidence slightly, but the naming convention and context of sibling search tools strongly indicate a safe read-only operation for discovering available models.
From the tool's definition Tool name 'search_models' indicates a search/discovery operation within ModelScope's AI resources. Sibling tools include other read-only operations like 'search_datasets', 'search_papers', and 'search_studios', establishing a pattern of data retrieval.
Documented attack patterns abuse exactly the kind of access search_models gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ModelScope MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_models:
{
"version": "1",
"default": "deny",
"tools": {
"search_models": {}
}
}search_models 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.
search_models. It is categorised as a Read tool in the ModelScope MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ModelScope MCP Server MCP server in PolicyLayer and add a rule for search_models: 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 ModelScope MCP Server. Nothing to install.
search_models 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 search_models 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 search_models. 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.
search_models is provided by the ModelScope MCP Server MCP server (modelscope/modelscope-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ModelScope 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.
9 ModelScope MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.