MCP-CLIO
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP-CLIOrestart the dev environment"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP-CLIO
A Model Context Protocol (MCP) server that exposes CLIO (Creatio CLI) commands as tools for AI agents.
Features
Stateless HTTP MCP Server - Streamable HTTP transport for reliable communication
Environment Management -
clio-environmenttool for ping and restart operationsRaw Command Escape Hatch -
clio-rawtool for executing any CLIO commandExtensible Architecture - Modular tool structure ready for additional CLIO commands
Related MCP server: linux-harness-mcp
Prerequisites
Node.js >= 18
CLIO installed globally:
dotnet tool install clio -gRegistered Creatio environments (via
clio reg-web-app)
Installation
npm install
npm run buildUsage
Start the server:
npm startThe server will listen on http://localhost:3000/mcp (configurable via PORT environment variable).
Available Tools
clio-environment
Manage Creatio environments:
ping - Check environment health
restart - Restart web application
Parameters:
command:"ping"|"restart"environment: Environment name (registered viaclio reg-web-app)
clio-raw
Execute any CLIO command with custom arguments:
Parameters:
command: Full command string (e.g.,"get-pkg-list -e myenv")
Project Structure
mcp-clio/
├── src/
│ ├── index.ts # Express server entry point
│ ├── server.ts # MCP server factory
│ ├── clio/
│ │ └── executor.ts # CLIO command executor
│ └── tools/
│ ├── environment.ts # Environment management tools
│ ├── raw.ts # Raw command escape hatch
│ └── *.ts # Placeholder tool modules
├── package.json
├── tsconfig.json
└── PLAN.md # Implementation planTesting with MCP Client
The project includes an mcp.json configuration for local testing. To use it:
Start the server in one terminal:
npm startIn another application (Claude Desktop, etc.), reference this server using the
mcp.jsonconfiguration:{ "mcpServers": { "mcp-clio": { "url": "http://localhost:3000/mcp" } } }
Development
# Build TypeScript
npm run build
# Run after building
npm start
# Build and run
npm run devLicense
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Exposes FEDLIN's public security scanners as agent-callable tools over Streamable HTTP.
Deploy and manage Jade Hosting projects from AI clients. Jade account and OAuth required.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI tools like Claude to interact with a remote machine's file system and shell via a secure HTTPS endpoint. It provides standardized tools for executing shell commands, reading and writing files, and navigating directories.-
- AlicenseNot gradedqualityDmaintenanceExposes a Linux host with shell, Python, and filesystem tools as MCP tools over HTTPS, enabling AI agents to execute commands and manage files remotely.5 npmMIT
- FlicenseNot gradedqualityAmaintenanceEnables MCP-compatible AI clients to invoke CLI-driven agent tools over Streamable HTTP, including shell execution, file operations, patching, image viewing, web search, and nested agent tasks, with permission modes and real-time progress streaming.-
- AlicenseAqualityAmaintenanceEnables AI clients to perform Sisense environment operations such as governance, asset and user/group management, lifecycle tasks, and health checks using the calling user's own credentials.36MIT