Execute arbitrary JavaScript code in the VSCode window context (like DevTools console). Has full access to document, window, and all globals. Returns the result as JSON.
AI agents invoke vscode_execute_script to trigger actions in VSCode Automation MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool permits execution of arbitrary JavaScript in the VSCode application context, which can inspect and modify any data accessible to VSCode, read file contents, manipulate the DOM, trigger VSCode commands, and potentially escape to host system operations.
From the tool's definition Tool description explicitly states 'Execute arbitrary JavaScript code' with 'full access to document, window, and all globals.' The capability to run arbitrary code in the VSCode window context is the definition of code execution.
Documented attack patterns abuse exactly the kind of access vscode_execute_script 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_execute_script:
{
"version": "1",
"default": "deny",
"tools": {
"vscode_execute_script": {
"limits": [
{
"counter": "vscode_execute_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}vscode_execute_script stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute arbitrary JavaScript code in the VSCode window context (like DevTools console). Has full access to document, window, and all globals. Returns the result as JSON. It is categorised as a Execute tool in the VSCode Automation MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VSCode Automation MCP server in PolicyLayer and add a rule for vscode_execute_script: 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_execute_script is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vscode_execute_script 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_execute_script. 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_execute_script 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.