AI agents call search_interfaces_by_uri 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 is a query/search operation that retrieves interface definitions based on URI patterns. It reads data from the NEI project without modifying, deleting, or executing code. The tool is purely informational with no capability to change state or trigger external operations. Low severity due to limited blast radius of a search operation.
From the tool's definition Tool performs 'fuzzy search' (模糊搜索) by URI/path within NEI project interfaces; described as matching 'interface path' only without side effects
Attacks that exploit this kind of access
通过接口定义的URI（访问路径）在NEI项目中进行模糊搜索。此工具只匹配接口path，不处理NEI详情页链接；如果用户提供的是 /interface/detail/?pid=10135&id=13015 或完整详情页URL，应改用. 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_uri: 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_uri 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_uri 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_uri. 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_uri 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 →