aicommander-connect
mcpsmitheryAI Commander is a remote shell for AI agents. It lets an MCP client (Claude, Codex, ChatGPT, Cursor, or any Model Context Protocol client) run shell commands on machines you own by quoting a short session code like `AIC-7K3P-WX9M-RTBN`. A small agent on the target machine keeps one outbound WebSocket open to AI Commander's hosted relay, so there are no inbound ports, no exposed SSH, and no VPN. Command stdout/stderr stream back in real time over SSE.
By Smithery | 9 findings | Scanned 7/3/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Needs ApprovalExcessive Permissions plus Dep Visibility 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 (9)
remote_exec:possible prompt injection detected in tool description: pattern matched: (?i)exfiltrate\s+(?:\w+\s+){0,2}(?:data|info|credentials?|secrets?|content|results?)
Fix: Remove adversarial instructions from tool descriptions. Validate all tool-definition strings against a safe-pattern allowlist before registration.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
session_statusremote_screenshotFix: 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.
declared capabilities: code/command execution, network access, filesystem access, database access, HTTP requests
remote_execdeclared capabilities: network access
session_statusremote_screenshotFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
remote_execsession_statusremote_screenshotFix: Review and remediate the identified issue.
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 aicommander-connect"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)