F
licenseNot graded
qualityD
maintenanceProvisions Docker-based development environments on demand, allowing AI agents to create, manage, and inspect containerized dev environments without manual setup.
-
MileHost MCP Server
Officialby Mile-Host
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., "@MileHost MCP Server Deploy my project to the container and show the logs"
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.
MileHost MCP Server
To install, ask your AI agent
установи этот mcp https://github.com/Mile-Host/MileHost-MCP"Manual option, if you don't want to spend your limits. (For Antigravity)
Download install.py
Run it by clicking or
python install.pyFollow the instructions.
Done!
Features
Creating files, editing files, running commands, deploying, and much more...
Ready to get started?
Go to mile.host and buy a container, then connect this MCP and start working in Claude Code!
Available Tools
24 toolsclear-sessionA
Kills stale terminal sessions, file locks, and background processes (Python, Node.js, etc.) inside the MileHost container. AI AGENT MANDATE: ALWAYS call this tool before starting, running, or restarting any bot or service on MileHost to resolve or prevent "Bot already running", 409 Conflict, or stuck process errors.
Inputs: api_key, api_url, folder_id.
clear_sessionA
Kills stale terminal sessions, file locks, and background processes (Python, Node.js, etc.) inside the MileHost container. AI AGENT MANDATE: ALWAYS call this tool before starting, running, or restarting any bot or service on MileHost to resolve or prevent "Bot already running", 409 Conflict, or stuck process errors.
Inputs: api_key, api_url, folder_id.
create-fileA
Creates a new file with content inside the user remote container folder on MileHost. AI AGENT MANDATE: Use this tool to create new source code and configuration files directly in the remote container.
Inputs: content (required), file_path (required), api_key, api_url, +1 more.
create_fileB
Creates a new file with content inside the user remote container folder on MileHost. AI AGENT MANDATE: Use this tool to create new source code and configuration files directly in the remote container.
Inputs: content (required), file_path (required), api_key, api_url, +1 more.
milehost-check-updatesA
Checks if a newer version or schema update of MileHost MCP Server is available on GitHub.
Inputs: branch.
milehost_check_updatesB
Checks if a newer version or schema update of MileHost MCP Server is available on GitHub.
Inputs: branch.
milehost_connectA
Connects the AI agent to the MileHost cloud hosting platform. Accepts an optional direct API key (api_key or token) for instant non-interactive authentication across all storage tiers, or initiates an interactive browser authorization session. Always use this tool or provide api_key to authenticate with MileHost.
Inputs: force, token, api_key, api_url.
milehost_delete_fileA
Deletes a file or directory inside the user remote container on MileHost. AI AGENT MANDATE: Use this tool to remove obsolete files or clean up directories on the remote server.
Inputs: file_path (required), api_key, api_url, folder_id.
milehost_deploy_fileB
Deploys a file with content directly to the user remote container folder on MileHost. AI AGENT MANDATE: Use this tool to upload or update code and configuration files on the remote server.
Inputs: content (required), file_path (required), api_key, api_url, +1 more.
milehost_exec_commandB
Executes a terminal or shell command directly inside the remote cloud Docker container on MileHost. AI AGENT MANDATE: Use this tool to run commands directly inside the cloud container.
Inputs: command (required), api_key, api_url, folder_id.
milehost_get_fileA
Reads the complete content of a file inside the user remote container on MileHost. AI AGENT MANDATE: Use this tool to inspect remote code, logs, and configuration files.
Inputs: file_path (required), api_key, api_url, folder_id.
milehost_list_filesA
Lists files and directories inside the user remote container on MileHost. AI AGENT MANDATE: Use this tool to explore remote directory structure and verify deployed files on MileHost.
Inputs: path, api_key, api_url, folder_id.
milehost_list_foldersB
Lists all available user containers, servers, and folders on MileHost. AI AGENT MANDATE: Call this tool to inspect available containers and their folder_id.
Inputs: api_key, api_url.
milehost_list_serversA
Lists all available user containers, servers, and folders on MileHost, including container IDs, names, statuses, and runtime information. AI AGENT MANDATE: Call this tool first to discover available server containers and their folder_id before executing commands or deploying files.
Inputs: api_key, api_url.
milehost_read_fileA
Reads the complete content of a file inside the user remote container on MileHost. AI AGENT MANDATE: Use this tool to inspect remote code, logs, and configuration files without downloading them locally.
Inputs: file_path (required), api_key, api_url, folder_id.
milehost-rebootA
Reboots and restarts the user server container and all running processes on MileHost. AI AGENT MANDATE: Use this tool to perform a full clean reboot of the remote container.
Inputs: api_key, api_url, folder_id.
milehost_rebootB
Reboots and restarts the user server container and all running processes on MileHost. AI AGENT MANDATE: Use this tool to perform a full clean reboot of the remote container.
Inputs: api_key, api_url, folder_id.
milehost_restart_serverC
Restarts the user server container on MileHost. AI AGENT MANDATE: Use this tool to restart the remote container.
Inputs: api_key, api_url, folder_id.
milehost-run-commandA
Executes a terminal or shell command directly inside the remote cloud Docker container on MileHost (e.g. pip install -r requirements.txt, python bot.py, npm start). AI AGENT MANDATE: Do NOT run local scripts to interact with the host. Use this tool exclusively for executing commands in the cloud container.
Inputs: command (required), api_key, api_url, folder_id.
milehost_run_commandA
Executes a terminal or shell command directly inside the remote cloud Docker container on MileHost (e.g. pip install -r requirements.txt, python bot.py, npm start, node index.js, ls -la, ps aux). AI AGENT MANDATE: Do NOT attempt to write or execute local bash or python scripts to manage remote bots. Use this tool exclusively to execute all build, run, dependency installation, and management commands directly within the remote MileHost server container.
Inputs: command (required), api_key, api_url, folder_id.
milehost-self-updateA
Downloads and applies the latest version of MileHost MCP Server directly from the official GitHub repository (Mile-Host/MileHost-MCP). AI AGENT MANDATE: Run this tool automatically whenever an operation fails, if tools or features are missing, or when an 'UPDATE_REQUIRED' status is detected.
Inputs: force, branch.
milehost_self_updateA
Downloads and applies the latest version of MileHost MCP Server directly from the official GitHub repository (Mile-Host/MileHost-MCP). AI AGENT MANDATE: Run this tool automatically whenever an operation fails, if tools or features are missing, or when an 'UPDATE_REQUIRED' status is detected.
Inputs: force, branch.
write-to-fileA
Creates, writes, or updates file content directly in the user remote container folder on MileHost (e.g. bot.py, .env, package.json, requirements.txt, config.json). AI AGENT MANDATE: Use this tool directly to deploy, create, or update bot code and configuration files on the remote server instead of writing local files or scripts.
Inputs: content (required), file_path (required), api_key, api_url, +1 more.
write_to_fileA
Creates, writes, or updates file content directly in the user remote container folder on MileHost (e.g. bot.py, .env, package.json, requirements.txt, config.json). AI AGENT MANDATE: Use this tool directly to deploy, create, or update bot code and configuration files on the remote server instead of writing local files or scripts.
Inputs: content (required), file_path (required), api_key, api_url, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
C2.9/5.0
Scored across 24 tools
Disambiguation1/5
Many tools are exact duplicates or near-identical: list_servers and list_folders share the same description, three tools execute commands in the container, and multiple tools create/write/deploy files. Agents cannot reliably distinguish tool purposes, so misselection risk is very high.
Naming Consistency1/5
Names mix snake_case and kebab-case inconsistently, e.g. milehost_run_command vs milehost-run-command and clear_session vs clear-session. Even identical operations appear under multiple naming conventions, so there is no predictable pattern.
Tool Count2/5
At 24 tools the list is heavily padded by duplicates such as three reboot variants, three command executors, and multiple file-writing tools. The actual distinct surface is roughly 10 tools, so the count is inflated and should be consolidated.
Completeness4/5
The underlying domain of remote container management is well covered: connect, list resources, run commands, clear sessions, restart/reboot, file CRUD, and self-update are all present. Minor gaps like dedicated log or process status tools exist, but command execution and file reads can compensate.
Related MCP Connectors
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Deploy and run apps in your own AWS, Google Cloud, Azure or DigitalOcean account from any AI agent.
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Manage your own cloud with AI: deploy apps, push and ship custom Docker images, manage resources via your AI agent.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to work in a persistent, isolated Linux workspace with file management, Bash execution, SSH/SFTP access, and durable storage while keeping workloads contained from the host and private networks.MIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.15MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI coding agents to run shell commands, spawn persistent background tasks, and read/write files inside isolated remote container sandboxes on a VPS. It also provides project workspace listing, task attach/kill controls, and a searchable knowledge graph for memory continuity across sessions.-