Execute VSCode commands with arguments **Common Use Cases:** - Format code: 'editor.action.formatDocument' with args: '[]' - Open files: 'vscode.open' with args: '["file:///absolute/path/to/file.ts"]' - Save all files: 'workbench.action.files.saveAll' with args: '[]' - Auto-fix issues: 'editor.ac...
Accepts freeform code/query input (command); Bulk/mass operation — affects multiple targets
Part of the Vscode MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents may call execute_command to permanently remove or destroy resources in Vscode. Without a policy, an autonomous agent could delete critical data in a loop with no way to undo the damage. Intercept blocks destructive tools by default and requires explicit human approval before enabling them.
Without a policy, an AI agent could call execute_command in a loop, permanently destroying resources in Vscode. There is no undo for destructive operations. Intercept blocks this tool by default and only allows it when a human explicitly approves the action.
Destructive tools permanently remove data. Block by default. Only enable with explicit approval workflows.
tools:
execute_command:
rules:
- action: deny
reason: "Blocked by default — enable with approval"See the full Vscode policy for all 8 tools.
Agents calling destructive-class tools like execute_command have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Destructive risk category across the catalogue. The same policy patterns (deny, require_approval) apply to each.
execute_command is one of the critical-risk operations in Vscode. For the full severity-focused view — only the critical-risk tools with their recommended policies — see the breakdown for this server, or browse all critical-risk tools across every MCP server.
Execute VSCode commands with arguments **Common Use Cases:** - Format code: 'editor.action.formatDocument' with args: '[]' - Open files: 'vscode.open' with args: '["file:///absolute/path/to/file.ts"]' - Save all files: 'workbench.action.files.saveAll' with args: '[]' - Auto-fix issues: 'editor.action.fixAll' with args: '[]' - Restart TypeScript: 'typescript.restartTsServer' with args: '[]' - Restart ESLint: 'eslint.restart' with args: '[]' **Important Notes:** - Commands and arguments may change with VSCode updates, it's recommended to search in the VSCode official repository to confirm the command and arguments are correct before use - Commands like 'reloadWindow', 'reloadExtensionHost' will interrupt conversation - ⚠️ WARNING: May cause irreversible changes, use with caution . It is categorised as a Destructive tool in the Vscode MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Add a rule in your Intercept YAML policy under the tools section for execute_command. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Vscode MCP server.
execute_command is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the execute_command rule in your Intercept 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 Intercept policy for execute_command. 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.
execute_command is provided by the Vscode MCP server (@vscode-mcp/vscode-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.