Home / MCP registry index / io.github.loved0543-dotcom/no-shell-agent-architect-mcp
No-Shell Agent Architect MCP
io.github.loved0543-dotcom/no-shell-agent-architect-mcp in the official MCP registry.
Endpoint https://ai-automation-operating-pack.vercel.app/api/mcp. Source: github.com/loved0543-dotcom/no-shell-agent-operating-pack.
The registry describes it as: Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
We read its 7 tools on 2026-10-26. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
design_automation_stack generate_no_shell_prompt recommend_agent_tools audit_automation_plan build_validation_pack build_customer_intake build_m2m_package_contract
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-loved0543-dotcom-no-shell-agent-architect-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.