Sandbox Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHAT_MODEL | No | Model name | gpt-4o |
| CHAT_MODEL_API_KEY | Yes | API key for the LLM provider (required) | |
| CHAT_MODEL_BASE_URL | No | Custom API base URL (optional) | |
| CHAT_MODEL_PROVIDER | No | Provider: openai, anthropic, google_genai, ollama | openai |
| CHAT_MODEL_SUPPORTS_VISION | No | Override vision detection (true/false, empty = auto) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_sessionA | Creates an isolated sandbox environment (Docker container). |
| execute_codeA | Executes code in the sandbox. State persists across calls (like Jupyter cells). |
| execute_terminalA | Runs a shell command inside the sandbox. |
| import_filesA | Imports files into the sandbox from host or from another session. |
| export_filesA | Registers files for download and cross-session import (no host copy). |
| stop_sessionA | Stops and removes the sandbox completely. Use when done with a session. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clear, distinct purpose: creating sessions, executing code, running terminal commands, exporting/importing files, and stopping sessions. No overlap in functionality.
All tool names follow a consistent verb_noun pattern (e.g., create_session, execute_code) with clear action and target.
6 tools is appropriate for a sandbox management server, covering the full lifecycle and common operations without being excessive or sparse.
The set covers the complete sandbox workflow: creation, code execution, terminal access, file import/export, and teardown. No obvious gaps.