ToolTrust
A2/100
Smithery

luther-systems-insideout

mcpsmithery

@Smithery

Conversational AI agent that designs AWS or GCP infrastructure end-to-end — describe your application in plain English, and Riley designs the architecture, generates production-ready Terraform, estimates monthly costs, and deploys. ## Highlights - **24 tools** across design, deployment, and post-deploy infrastructure inspection - Coverage of 50+ AWS and GCP services - Module-by-module Terraform output (networking, compute, storage, auth, observability, …) - Cost estimates broken down per component before any deploy - One-command provisioning to AWS or GCP, then live monitoring + drift detection - No Terraform expertise required ## Hosted Streamable HTTP, no-auth required: `https://app.luthersystems.com/v1/insideout-mcp` ## Other listings - **mcp.so:** https://mcp.so/server/insideout - **Glama:** https://glama.ai/mcp/servers/luthersystems/insideout-agent-skills - **Official MCP Registry:** `com.luthersystems.insideout/mcp` ## Source Skills bundle and MCP discovery artifacts: https://github.com/luthersystems/insideout-agent-skills

By Smithery | 43 findings | Scanned 6/28/2026 | tooltrust-scanner/v0.3.19

7 Low36 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (43)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×7

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    awsinspectawsinspect_batchconvoopengcpinspectgcpinspect_batchtfdeploytfgenerate

    Fix: 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.

  • InfoAS-002

    ⚠️Excessive Permissions ×11

    declared capabilities: network access

    awsinspectawsinspect_batchcredawait

    declared capabilities: network access, database access

    convoopen

    declared capabilities: filesystem access

    convoreply

    declared capabilities: database access

    convostatus

    declared capabilities: network access, database access, HTTP requests

    gcpinspectgcpinspect_batch

    declared capabilities: network access, filesystem access

    tfdeploytfgenerate

    declared capabilities: network access, HTTP requests

    tflogs

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×24

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    awsinspectawsinspect_batchconvoawaitconvoinspectconvoopenconvoreplyconvostatuscredawaitgcpinspectgcpinspect_batchhelpstackdiffstackrollbackstackversionssubmit_feedbacktfdeploytfdestroytfdrifttfgeneratetflogstfoutputstfplantfrunstfstatus

    Fix: Review and remediate the identified issue.

  • InfoAS-006

    💻Arbitrary Code Execution

    tfgenerate:tool name or description implies arbitrary script/code execution — capability unconfirmed (no exec permission or code/script/eval input property found)

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

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 luther-systems-insideout"

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.

[![ToolTrust Grade A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)