vscode-mcp-server
mcp0.4.0MCP server to expose VS Code editing features to an LLM for AI coding
By juehang | 22 findings | Scanned 6/3/2026 | tooltrust-scanner/v0.3.13 | 370
Risk Summary
Needs ApprovalExcessive Permissions plus Supply Chain CVEs raises enough risk that this tool should not be auto-trusted.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (22)
tool declares exec permission
execute_shell_commandcreate_diffFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
GO-2026-5024 in golang.org/x/[email protected]: Invoking integer overflow in NewNTUnicodeString in golang.org/x/sys/windows (upgrade to 0.44.0)
execute_shell_commandcreate_diffopen_fileopen_projectcheck_extension_statusget_extension_portlist_available_projectsget_active_tabsget_context_tabsFix: Upgrade or replace the vulnerable dependency. Pin all dependency versions and enable automated CVE scanning (Dependabot or OSV Scanner).
tool declares fs permission
execute_shell_commandcreate_diffopen_fileopen_projectcheck_extension_statusget_extension_portlist_available_projectsget_active_tabsget_context_tabsFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
execute_shell_commandcreate_diffFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y vscode-mcp-server"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)