No-Shell Agent Architect MCP

A remote MCP server that converts vague automation requests into concrete agent workflows, providing tool stacks, prompts, permissioned account routes, dry-run paths, validation checks, and recovery plans to prevent empty-shell AI automation.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Community listingStreamable HTTPNo sign-inEndpoint checked 2026-11-07Published by loved0543-dotcom

MCP endpoint (Streamable HTTP)

https://ai-automation-operating-pack.vercel.app/api/mcp

Vendor documentation

What its tools do

7 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Not annotated (7)

design_automation_stack
generate_no_shell_prompt
recommend_agent_tools
audit_automation_plan
build_validation_pack
build_customer_intake
build_m2m_package_contract

7 of 7 have a description · 0 of 7 declare behavior hints · 1 of 7 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

Passed Endpoint answered the live check · Nov 7, 2026, 1:18 AM UTC
Availability 1 of 1 checks passed in 30 days

What you can do with it

Route vague workflow requests into concrete automation architecture
Generate copy-paste commands for agents like Codex or Claude
Audit automation plans for shell-risk and missing execution pieces
Build validation packs with dry-run and QA criteria

Source and maintenance

Community listingRegistry 0.1.2

mcp-registry: io.github.loved0543-dotcom/no-shell-agent-architect-mcp@0.1.2 Source repository

Maintenance checked: Nov 7, 2026, 12:20 AM UTC

Protocol and capabilities

Server: no-shell-agent-architect-mcp 0.1.2
MCP protocol negotiated in check: 2025-11-25
Tools: 7 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  }
}

Tools

7 advertised

design_automation_stack — Design Automation Stack

Advertised by the server during the last successful anonymous check.

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

design_automation_stack input schema

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

generate_no_shell_prompt — Generate No-Shell Prompt

Advertised by the server during the last successful anonymous check.

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

generate_no_shell_prompt input schema

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

recommend_agent_tools — Recommend Agent Tools

Advertised by the server during the last successful anonymous check.

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

recommend_agent_tools input schema

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

audit_automation_plan — Audit Automation Plan

Advertised by the server during the last successful anonymous check.

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

audit_automation_plan input schema

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

build_validation_pack — Build Validation Pack

Advertised by the server during the last successful anonymous check.

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

build_validation_pack input schema

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

build_customer_intake — Build Customer Intake

Advertised by the server during the last successful anonymous check.

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

build_customer_intake input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "goal": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

build_m2m_package_contract — Build M2M Package Contract

Advertised by the server during the last successful anonymous check.

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.

build_m2m_package_contract input schema

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

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 414 ms
95th percentile latency: 414 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 7, 2026, 1:18 AM UTC · probe · passed · 414 ms · metadata changed · 7 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

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

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add no-shell-agent-architect-mcp --url https://ai-automation-operating-pack.vercel.app/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable no-shell-agent-architect-mcp in your MCP settings.

Cursor configuration

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

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "no-shell-agent-architect-mcp": {
      "type": "streamableHttp",
      "url": "https://ai-automation-operating-pack.vercel.app/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start no-shell-agent-architect-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "no-shell-agent-architect-mcp": {
      "type": "http",
      "url": "https://ai-automation-operating-pack.vercel.app/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

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

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.

Claude Desktop configuration

https://ai-automation-operating-pack.vercel.app/api/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "no-shell-agent-architect-mcp": {
      "serverUrl": "https://ai-automation-operating-pack.vercel.app/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like No-Shell Agent Architect MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows