mcpwatch

← All servers

Grade B

No-Shell Agent Architect MCP

io.github.loved0543-dotcom/no-shell-agent-architect-mcp · v0.1.2 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.

Source: https://github.com/loved0543-dotcom/no-shell-agent-operating-pack

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 7 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (generate_no_shell_prompt). Require confirmation before the agent calls them.

What was checked

Public tools: design_automation_stack, generate_no_shell_prompt, recommend_agent_tools, audit_automation_plan, build_validation_pack, build_customer_intake, build_m2m_package_contract

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-loved0543-dotcom-no-shell-agent-architect-mcp-5327bfa0.svg)](https://www.mcpwatch.io/s/io-github-loved0543-dotcom-no-shell-agent-architect-mcp-5327bfa0)