// MCP TOOL REFERENCE

execute_shell_command_code

ServerVscode
CategoryExecute

How to control execute_shell_command_code ↓

WHAT IT DOES

What execute_shell_command_code does on Vscode

AI agents invoke execute_shell_command_code to trigger actions in Vscode. 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.

THE RISK

High Risk

Why execute_shell_command_code needs a policy

This tool allows execution of arbitrary shell commands with side effects determined entirely by the arguments provided. An AI agent could misuse this to install malware, exfiltrate data, modify system files, or compromise the development environment. The blast radius is critical because shell access in a development environment enables complete system compromise.

From the tool's definition Tool description explicitly states it 'Executes shell commands in VS Code integrated terminal' with capabilities including 'Running CLI commands, builds, git operations, npm/pip installs.' The ability to run arbitrary shell commands with configurable working…

Risk signalsAdmin/system-level operation

Documented attack patterns abuse exactly the kind of access execute_shell_command_code gives an agent:

POLICY

How to control execute_shell_command_code

PolicyLayer is an MCP gateway — it sits between your AI agents and Vscode, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_shell_command_code:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "execute_shell_command_code": {
      "limits": [
        {
          "counter": "execute_shell_command_code_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

execute_shell_command_code 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.

Create a free account and register Vscode — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Vscode tools

Write copy_file_code Copies a file to a new location. WHEN TO USE: Creating backups, duplicating files Write create_file_code Creates new files or completely rewrites existing files. WHEN TO USE: New files, Write move_file_code Moves a file or directory to a new location using VS Code Write rename_file_code Renames a file or directory using VS Code Write replace_lines_code Replaces specific lines in existing files with exact content validation. WHEN TO Read get_diagnostics_code CRITICAL: Run this after EVERY series of code changes to check for errors before completin Read get_document_symbols_code Gets complete symbol outline for a file showing hierarchical structure and line numbers. Read get_symbol_definition_code Gets definition information for a symbol using hover data (type, docs, source). W

All 12 Vscode tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Vscode → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about execute_shell_command_code

What does the execute_shell_command_code tool do? +

Executes shell commands in VS Code integrated terminal. WHEN TO USE: Running CLI commands, builds, git operations, npm/pip installs. Working directory: Use cwd to run commands in specific directories. Defaults to workspace root. If you get unexpected results, ensure the cwd is correct. Timeout: Commands must complete within specified time (default 10s) or the tool will return a timeout error, but the command may still be running in the terminal. It is categorised as a Execute tool in the Vscode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_shell_command_code? +

Register the Vscode MCP server in PolicyLayer and add a rule for execute_shell_command_code: 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.

What risk level is execute_shell_command_code? +

execute_shell_command_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit execute_shell_command_code? +

Yes. Add a rate_limit block to the execute_shell_command_code 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.

How do I block execute_shell_command_code completely? +

Set action: deny in the PolicyLayer policy for execute_shell_command_code. 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.

What MCP server provides execute_shell_command_code? +

execute_shell_command_code is provided by the Vscode MCP server (juehang/vscode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.