8 tools. 3 can modify or destroy data without limits.
1 destructive tool with no built-in limits. Policy required.
Last updated:
Destructive tools (execute_command) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (open_files, rename_symbol) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Intercept sits between your agent and Vscode. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.
npx -y @policylayer/intercept scan -- npx -y @vscode-mcp/vscode-mcp-server execute_command:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
open_files:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
get_diagnostics:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Vscode server exposes 1 destructive tools including execute_command. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Vscode server has 2 write tools including open_files, rename_symbol. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
8 tools across 3 categories: Destructive, Read, Write. 5 are read-only. 3 can modify, create, or delete data.
One line change. Instead of running the Vscode server directly, prefix it with Intercept: intercept -c vscode.yaml -- npx -y @@vscode-mcp/vscode-mcp-server. Download a pre-built policy from policylayer.com/policies/vscode and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Set budgets, approvals, and hard limits across MCP servers.
See what your agent can donpx -y @policylayer/intercept