AI agents call search_interfaces_by_name to retrieve information from Nei without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves interface information based on business name or functional description. It only queries data and returns results without creating, modifying, deleting, or executing any operations. This is a standard Read category operation with low blast radius if misused by an AI agent.
From the tool's definition The tool description indicates it performs a 'fuzzy search' (模糊搜索) through NEI project interfaces by business name. This is a retrieval/query operation with no side effects mentioned.
Attacks that exploit this kind of access
通过接口的业务名称在NEI项目中进行模糊搜索。当你知道接口的功能描述或业务名称（通常是中文）时，应优先使用此工具。如果搜索结果为空，建议先调用. It is categorised as a Read tool in the Nei MCP Server, which means it retrieves data without modifying state.
Register the Nei MCP server in PolicyLayer and add a rule for search_interfaces_by_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 Nei. Nothing to install.
search_interfaces_by_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 search_interfaces_by_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 search_interfaces_by_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.
search_interfaces_by_name is provided by the Nei MCP server (@leila329/nei-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →