Skip to content

No-Shell Agent Architect MCP

by loved0543-dotcom · remote · no sign-in to list tools · v0.1.2 · published by GitHub user loved0543-dotcom

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

Changes · 6
CompareRegistry entry

7 tools: 6 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http no-shell-agent-architect https://ai-automation-operating-pack.vercel.app/api/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

7 tools

Changes things 6Claude Code: ask
  • audit_automation_planScore an existing automation plan for shell-risk, missing inputs, missing validation, missing tool route, and missing recovery path.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Score an existing automation plan for shell-risk, missing inputs, missing validation, missing tool route, and missing recovery path.
  • build_customer_intakeGenerate a 10-minute intake questionnaire for a non-developer who wants one workflow automated.No findings

    Why it is in this group

    • The description's first verb is "generate": a word for a change.
    Description, as the server wrote it
    Generate a 10-minute intake questionnaire for a non-developer who wants one workflow automated.
  • build_m2m_package_contractCreate a machine-readable package contract for agencies, SaaS builders, or other agents that want to integrate the No-Shell operating pack through MCP/API plus human-readable deliv…No findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.
    Description, as the server wrote it
    Create a machine-readable package contract for agencies, SaaS builders, or other agents that want to integrate the No-Shell operating pack through MCP/API plus human-readable delivery artifacts.
  • design_automation_stackTurn a vague automation request into a tool/MCP/plugin/skill stack, permissioned account route, workflow phases, validation pack, and live-action boundary.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Turn a vague automation request into a tool/MCP/plugin/skill stack, permissioned account route, workflow phases, validation pack, and live-action boundary.
  • generate_no_shell_promptCreate a copy-paste natural-language command that tells an agent how to execute the workflow without producing an empty shell.No findings

    Why it is in this group

    • The name "generate_no_shell_prompt" says "generate": a word for a change.
    Description, as the server wrote it
    Create a copy-paste natural-language command that tells an agent how to execute the workflow without producing an empty shell.
  • recommend_agent_toolsRecommend MCP servers, Codex plugins, skills, permissioned account routes, and live-action boundaries for a requested automation.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Recommend MCP servers, Codex plugins, skills, permissioned account routes, and live-action boundaries for a requested automation.
Only reads 1Claude Code: allow
  • build_validation_packReturn dry-run, QA, audit, and PASS criteria for one automation workflow.No findings

    Why it is in this group

    • The description's first verb is "return": a word for reading.
    Description, as the server wrote it
    Return dry-run, QA, audit, and PASS criteria for one automation workflow.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Install

Pinned to version 0.1.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http no-shell-agent-architect https://ai-automation-operating-pack.vercel.app/api/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__no-shell-agent-architect__build_validation_pack"
    ],
    "ask": [
      "mcp__no-shell-agent-architect__design_automation_stack",
      "mcp__no-shell-agent-architect__generate_no_shell_prompt",
      "mcp__no-shell-agent-architect__recommend_agent_tools",
      "mcp__no-shell-agent-architect__audit_automation_plan",
      "mcp__no-shell-agent-architect__build_customer_intake",
      "mcp__no-shell-agent-architect__build_m2m_package_contract"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as no-shell-agent-architect. Review it before you use it.