AI agents call list_enemies_mcp to retrieve information from Doctah-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against Arknights game data, returning a filtered list of enemies based on fuzzy search criteria. There are no side effects, data modifications, code execution, or destructive actions involved. It is purely a retrieval mechanism for public game information.
From the tool's definition Tool name 'list_enemies_mcp' and description '搜索相关敌人并返回敌人名称列表（模糊搜索）' [Search related enemies and return enemy name list (fuzzy search)] indicate a search/query operation that retrieves game data without modification or execution.
Documented attack patterns abuse exactly the kind of access list_enemies_mcp gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Doctah-MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for list_enemies_mcp:
{
"version": "1",
"default": "deny",
"tools": {
"list_enemies_mcp": {}
}
}list_enemies_mcp 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.
搜索相关敌人并返回敌人名称列表（模糊搜索）. It is categorised as a Read tool in the Doctah-MCP MCP Server, which means it retrieves data without modifying state.
Register the Doctah- MCP server in PolicyLayer and add a rule for list_enemies_mcp: 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 Doctah-MCP. Nothing to install.
list_enemies_mcp 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 list_enemies_mcp 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 list_enemies_mcp. 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.
list_enemies_mcp is provided by the Doctah- MCP server (tonybotni/doctah-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Doctah-MCP, 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.
14 Doctah-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.