搜尋 MDN Web Docs 文件，取得最新的 API 資訊、用法說明、棄用狀態和瀏覽器相容性
AI agents call search_mdn to retrieve information from Dev Advisor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves documentation information from MDN Web Docs without side effects. It returns reference data about APIs, usage, deprecation status, and browser compatibility—all read-only operations. No data creation, modification, code execution, or destructive actions are possible through this tool.
From the tool's definition Tool description indicates 'search' and 'retrieve' operations: 'searches MDN documentation', 'fetch API information' (搜尋 MDN Web Docs 文件，取得最新的 API 資訊). No modification, execution, deletion, or financial operations are mentioned.
Attacks that exploit this kind of access
搜尋 MDN Web Docs 文件，取得最新的 API 資訊、用法說明、棄用狀態和瀏覽器相容性. It is categorised as a Read tool in the Dev Advisor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Dev Advisor MCP Server MCP server in PolicyLayer and add a rule for search_mdn: 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 Dev Advisor MCP Server. Nothing to install.
search_mdn 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_mdn 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_mdn. 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_mdn is provided by the Dev Advisor MCP Server MCP server (mukiwu/dev-advisor-mcp). 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 →