AI agents call cursor_editor_state to retrieve information from Vscode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and queries the current state of the VS Code editor without modifying, executing, or destructively altering any files or operations. It is purely informational, making it a Read category tool with low severity since it poses minimal risk even if accessed by an AI agent.
From the tool's definition Tool description states it retrieves editor state: 'Get the current editor state: active file, cursor position, selected text, open editors.' Uses 'Get' verb indicating query-only operation with no side effects.
Attacks that exploit this kind of access
Get the current editor state: active file, cursor position, selected text, open editors. It is categorised as a Read tool in the Vscode MCP Server, which means it retrieves data without modifying state.
Register the Vscode MCP server in PolicyLayer and add a rule for cursor_editor_state: 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. Nothing to install.
cursor_editor_state 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 cursor_editor_state 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 cursor_editor_state. 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.
cursor_editor_state is provided by the Vscode MCP server (kloutdevs/vscode-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 →