No-Shell Agent Architect MCP server
online · 100% uptimeio.github.loved0543-dotcom/no-shell-agent-architect-mcp·v0.1.2Turns vague automation requests into tool stacks, prompts, QA checks, and human boundaries.
0 stars
Reviews
Write oneNobody has reviewed No-Shell Agent Architect MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
No-Shell Agent Architect MCP tools (7, 2 write)
write = sends, deletes, buys or postsaudit_automation_planFreeScore an existing automation plan for shell-risk, missing inputs, missing validation, missing tool route, and missing recovery path.
build_customer_intakeFreeGenerate a 10-minute intake questionnaire for a non-developer who wants one workflow automated.
build_m2m_package_contractwrite actionFreeCreate 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.
build_validation_packFreeReturn dry-run, QA, audit, and PASS criteria for one automation workflow.
design_automation_stackFreeTurn 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_promptwrite actionFreeCreate a copy-paste natural-language command that tells an agent how to execute the workflow without producing an empty shell.
recommend_agent_toolsFreeRecommend MCP servers, Codex plugins, skills, permissioned account routes, and live-action boundaries for a requested automation.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 370ms20/20
- Tool poisoning7 tool descriptions checked15/15
- Auth qualityopen endpoint exposes 2 write-action tools with no auth3/15
- Maintenancelast push 104 days ago8/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (1)
- highWrite-action tools reachable without authentication
auth.open-write
How No-Shell Agent Architect MCP compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 72/100
- higher than 40% of 4,460 AI and agents servers
- Tools
- 7
- the typical AI and agents server has 6
- Tools that change things
- 29%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote AI and agents server answers 100%
- Response time
- 370 ms
- faster than 38% of 2,331 AI and agents servers
What its tools let an agent do: 5 read · 1 create · 1 change
Install No-Shell Agent Architect MCP in Claude Code, Cursor or VS Code
claude mcp add --transport http no-shell-agent-architect-mcp https://ai-automation-operating-pack.vercel.app/api/mcp
What the publisher says
From the No-Shell Agent Architect MCP repository's README, as published. We do not edit it. Read it on GitHub
No-Shell Agent Operating Pack
An open-source operating pack for people who already use AI agents but keep getting "empty-shell automation": files, buttons, or dashboards that look finished but do not actually run a real workflow.
This is not a prompt-pack that promises magic. It is a plain-language operating system for delegating work to ChatGPT, Claude, Codex, Gemini, Hermes, and similar agents with a real objective, inputs, tool choice, permissioned account route, validation, recovery, and live-action boundary.
No-Shell Agent Architect MCP
This repository now also ships a remote MCP/API product: No-Shell Agent Architect MCP.
Current launch mode: free public beta. There is no payment flow, usage gate, paid API call, or private customer data collection in this version. The goal is to observe GitHub stars, issues, workflow feedback, and real usage before deciding whether a paid version should exist later.
It takes a plain-language automation goal and returns:
- the recommended MCP/plugin/skill/tool stack;
- a copy-paste no-shell agent command;
- dry-run steps;
- QA and audit checks;
- recovery guidance;
- permissioned account routes and live-action boundaries for secrets, accounts, payments, publishing, and irreversible actions.
- a machine-readable M2M package contract for agencies, SaaS builders, and other agents that need to integrate the operating pack.
Local API preview:
npm install
npm run devThen open:
http://localhost:3000Canonical remote MCP endpoint:
https://ai-automation-operating-pack.vercel.app/api/mcpLive demo:
https://ai-automation-operating-pack.vercel.appLaunch kit:
https://ai-automation-operating-pack.vercel.app/launchPublic beta feedback:
https://github.com/loved0543-dotcom/no-shell-agent-operating-pack/issues/1Machine-readable M2M package contract:
https://ai-automation-operating-pack.vercel.app/api/m2m-packageOfficial MCP Registry:
https://registry.modelcontextprotocol.io/v0/servers?search=no-shell-agent-architect-mcpCompatibility URL:
https://no-shell-agent-architect-mcp.vercel.appThe compatibility URL is kept for old shared links only. New docs, client config, and registry metadata should use https://ai-automation-operating-pack.vercel.app.
Client config:
{
"mcpServers": {
"no-shell-agent-architect": {
"url": "https://ai-automation-operating-pack.vercel.app/api/mcp"
}
}
}Who this is for
- Non-developers, solo operators, freelancers, and small teams who want practical AI automation.
- People who know AI can code or automate, but do not know which plugin, skill, command, or workflow to start with.
- People who need "make this business workflow actually work", not only "generate some code".
What's included
- Free diagnostic: 10 reasons AI automations become empty shells.
- Free beta starter pack: Email and document automation workflow.
- Before/After demo: a shallow command vs a no-shell operating command.
- Customer intake sheet.
- Tool/router sheet for choosing agents, plugins, skills, MCP, browser, documents, spreadsheets, permissioned account connectors, or live-action review.
- Copy-paste command cards written in natural language.
- Result scorecard for catching fake completion.
- Recovery playbook: fix the upstream cause instead of stopping at one more gate.
- Permissioned connector v1 contract for Gmail/community account automation without password, cookie, or posting bypass.
- M2M package contract for MCP/API integrators, agencies, and builders.
- Validation tracker for a 20-person usefulness test.
- Public beta signal tracker for stars, issues, shares, and workflow feedback.
Quick start
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
No-Shell Agent Architect MCP: common questions
- Is No-Shell Agent Architect MCP server safe?
- Mostly: it is graded B (72/100). Read the No-Shell Agent Architect MCP safety report
- How do I install No-Shell Agent Architect MCP?
- It runs remotely at ai-automation-operating-pack.vercel.app. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does No-Shell Agent Architect MCP need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is No-Shell Agent Architect MCP maintained?
- The last commit was 142 days ago (2026-06-15). The latest release is v0.1.2.
- Is No-Shell Agent Architect MCP up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of No-Shell Agent Architect MCP?
- Servers from other publishers that do the same job: Agent-Native Analytics MCP server, Image MCP server and Emilia Protocol MCP server.
- How does No-Shell Agent Architect MCP compare with other AI and agents MCP servers?
- safety score 72/100 (higher than 40% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to No-Shell Agent Architect MCP
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native AnalyticsAgent-Native Amplitude/Mixpanel - connect data sources, prompt for chartsnot reviewedEstablishedA
- ImageAI image generation and editing with prompt optimization and quality presetsnot reviewedEstablishedB
- Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts.not reviewedEstablishedB
- CHAP CoordinatorAuditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.not reviewedEstablishedA
- llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.not reviewedEstablishedA