AI agents call cursor_status 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 queries the state of the Cursor extension and retrieves workspace metadata. It performs no modifications, executions, deletions, or financial operations. The only potential side effect would be information disclosure about the workspace structure, which is a low-severity risk in a local IDE context.
From the tool's definition Tool description states 'Check if the Cursor MCP Bridge extension is running and get workspace info.' The verbs 'check' and 'get' indicate read-only operations that retrieve status and workspace information without modifying or executing anything.
Attacks that exploit this kind of access
Check if the Cursor MCP Bridge extension is running and get workspace info. 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_status: 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_status 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_status 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_status. 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_status 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 →