Search the DOM for elements by text content, ID, class, aria-label, title, or role. Returns matching elements with their selectors.
AI agents call vscode_search_dom to retrieve information from VSCode Automation MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only introspection tool. It queries the VSCode UI DOM structure to locate elements based on various attributes (text, ID, class, aria-label, title, role) and returns results. No data is created, modified, deleted, or executed. While it's part of an automation server capable of controlling VSCode, this specific tool only retrieves information about the UI state.
From the tool's definition Tool performs DOM search and inspection, returning matching elements and selectors without modifying state. Description explicitly states it 'Search[es] the DOM for elements' and 'Returns matching elements'—pure query operation with no side effects.
Documented attack patterns abuse exactly the kind of access vscode_search_dom gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and VSCode Automation MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for vscode_search_dom:
{
"version": "1",
"default": "deny",
"tools": {
"vscode_search_dom": {}
}
}vscode_search_dom 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 the DOM for elements by text content, ID, class, aria-label, title, or role. Returns matching elements with their selectors. It is categorised as a Read tool in the VSCode Automation MCP MCP Server, which means it retrieves data without modifying state.
Register the VSCode Automation MCP server in PolicyLayer and add a rule for vscode_search_dom: 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 VSCode Automation MCP. Nothing to install.
vscode_search_dom 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 vscode_search_dom 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 vscode_search_dom. 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.
vscode_search_dom is provided by the VSCode Automation MCP server (sukarth/vscode-automation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from VSCode Automation 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.
61 VSCode Automation MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.