mcp-sandbox-computer-vm-for-ai
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLY_TOKEN | No | Fly API token for the Fly Machines backend. Alternative to FLY_API_TOKEN. | |
| FLY_REGION | No | Region for newly created Fly Machines. | |
| E2B_API_KEY | No | E2B API key for the E2B backend. | |
| FLY_APP_NAME | No | Fly App that owns sandbox Machines. | |
| FLY_API_TOKEN | No | Fly API token for the Fly Machines backend. Alternative to FLY_TOKEN. | |
| MODAL_TOKEN_ID | No | Modal token ID for the Modal backend, overriding default authentication. | |
| MODAL_TOKEN_SECRET | No | Modal token secret for the Modal backend, overriding default authentication. | |
| KILNTAINERS_AUTH_TOKEN | No | Bearer token for /mcp HTTP endpoint. Set to a random hex string to protect the MCP server. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {
"mimeTypes": [
"text/html;profile=mcp-app"
]
}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| sandbox_execA | Execute a shell command in an isolated Debian Linux sandbox. Commands run in bash. Each call is independent — no state (shell variables, working directory) persists between calls (however filesystem does persist). Use the working_directory parameter or chain commands with && to control execution context. To write files or pass data without shell escaping, use the stdin parameter (e.g., command="cat > file.txt" with content in stdin). Commands time out after 120 seconds by default (override with the timeout parameter for long-running operations). |
| computer_dashboardA | Open the interactive MCP App dashboard for listing computers, running terminal commands, restarting, factory-resetting, and deleting. |
| computer_listA | List all sandbox computers managed by the selected backend. |
| computer_createA | Create a temporary or permanent sandbox computer. If computer_id is omitted, a readable random slug is returned. |
| computer_restartA | Restart a computer without erasing its writable filesystem. |
| computer_factory_resetA | Erase a computer's writable filesystem and recreate it from the base image. |
| computer_deleteA | Permanently delete a computer and all of its writable state. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Sandbox Computer Dashboard | Interactive lifecycle and terminal dashboard for sandbox computers. |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/flujo-app/mcp-sandbox-computer-vm-for-ai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server