MCP MeasureMCP Measure

index observed

No-Shell Agent Architect MCP

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

Should I use this

Quality & Safety

A
Description quality
90%
Schema completeness
89%
Naming quality
94%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Findings (1)

  • LOWTool 'audit_automation_plan' description lacks action verbin audit_automation_plan

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~1,113Tokens (tool definitions)
~1.5 KBTypical response size
Moderate attention impact (0.87% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "no-shell-agent-architect-mcp": {
      "url": "https://no-shell-agent-architect-mcp.vercel.app/api/mcp"
    }
  }
}

Remote endpoints

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

What it can do

Tool inventory

Tools (7)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
⚪design_automation_stack(goal, userType, domain, currentTools, risk, ...)

Turn a vague automation request into a tool/MCP/plugin/skill stack, permissioned account route, workflow phases, validation pack, and live-action boundary.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 6,
      "description": "Plain-language automation goal."
    },
    "userType": {
      "type": "string",
      "description": "Non-developer, solo operator, small team, developer, agency, etc."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain hint such as email_docs, ecommerce_data, knowledge_base, coding."
    },
    "currentTools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tools/plugins/MCPs already available to the user."
    },
    "risk": {
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "ko",
        "en"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡generate_no_shell_prompt(goal, userType, domain, currentTools, risk, ...)

Create a copy-paste natural-language command that tells an agent how to execute the workflow without producing an empty shell.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 6,
      "description": "Plain-language automation goal."
    },
    "userType": {
      "type": "string",
      "description": "Non-developer, solo operator, small team, developer, agency, etc."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain hint such as email_docs, ecommerce_data, knowledge_base, coding."
    },
    "currentTools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tools/plugins/MCPs already available to the user."
    },
    "risk": {
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "ko",
        "en"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪recommend_agent_tools(goal, userType, domain, currentTools, risk, ...)

Recommend MCP servers, Codex plugins, skills, permissioned account routes, and live-action boundaries for a requested automation.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 6,
      "description": "Plain-language automation goal."
    },
    "userType": {
      "type": "string",
      "description": "Non-developer, solo operator, small team, developer, agency, etc."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain hint such as email_docs, ecommerce_data, knowledge_base, coding."
    },
    "currentTools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tools/plugins/MCPs already available to the user."
    },
    "risk": {
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "ko",
        "en"
      ]
    }
  },
  "required": [
    "goal"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪audit_automation_plan(plan)

Score an existing automation plan for shell-risk, missing inputs, missing validation, missing tool route, and missing recovery path.

Input Schema

{
  "type": "object",
  "properties": {
    "plan": {
      "type": "string",
      "minLength": 20,
      "description": "Automation plan or prompt to audit."
    }
  },
  "required": [
    "plan"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪build_validation_pack(goal, domain, risk)

Return dry-run, QA, audit, and PASS criteria for one automation workflow.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 6
    },
    "domain": {
      "type": "string"
    },
    "risk": {
      "type": "string"
    }
  },
  "required": [
    "goal"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
⚪build_customer_intake(goal)

Generate a 10-minute intake questionnaire for a non-developer who wants one workflow automated.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟡build_m2m_package_contract(goal, userType, domain, currentTools, risk, ...)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "goal": {
      "type": "string",
      "minLength": 6,
      "description": "Plain-language automation goal."
    },
    "userType": {
      "type": "string",
      "description": "Non-developer, solo operator, small team, developer, agency, etc."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain hint such as email_docs, ecommerce_data, knowledge_base, coding."
    },
    "currentTools": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tools/plugins/MCPs already available to the user."
    },
    "risk": {
      "type": "string",
      "enum": [
        "low",
        "medium",
        "high"
      ]
    },
    "language": {
      "type": "string",
      "enum": [
        "ko",
        "en"
      ]
    },
    "buyerType": {
      "type": "string",
      "description": "Agency, freelancer, SaaS builder, solo operator, internal ops team, etc."
    },
    "packageMode": {
      "type": "string",
      "description": "mcp_api, starter_pack, agency_workbench, connector_pack, or a custom packaging mode."
    }
  },
  "required": [
    "goal"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded7 tools
verifiedversion not recorded7 tools
verifiedversion not recorded7 tools
verifiedversion not recorded7 tools