AI agents call cursor_diagnostics 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 retrieves and queries diagnostic data (errors and warnings) from the IDE without causing side effects, creating, modifying, deleting data, or executing commands. It is a pure read operation that gathers information for display or analysis.
From the tool's definition Tool name 'cursor_diagnostics' and description 'Get all errors and warnings (diagnostics) from the IDE' indicate retrieval of diagnostic information with no modification or execution of external operations.
Attacks that exploit this kind of access
Get all errors and warnings (diagnostics) from the IDE. 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_diagnostics: 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_diagnostics 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_diagnostics 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_diagnostics. 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_diagnostics 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 →