agent-sandbox-mcp
by dhanababum
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_SANDBOX_REGION | No | AWS region | AWS default |
| AGENT_SANDBOX_WORKDIR | No | Default working directory inside the VM | /work |
| AGENT_SANDBOX_IMAGE_ARN | Yes | MicroVM image ARN | |
| AGENT_SANDBOX_VERIFY_TLS | No | Set '0' to skip TLS verification to the MicroVM endpoint (debug only) | 1 |
| AGENT_SANDBOX_MCP_HOST_PATHS | No | os.pathsep-separated allowlist for host copy operations | current working directory |
| AGENT_SANDBOX_EXECUTION_ROLE_ARN | Yes | Execution role ARN | |
| AGENT_SANDBOX_MCP_ENABLE_DANGEROUS | No | Reserved for future dangerous ops; destructive image ops still require confirm: true | 0 |
| AGENT_SANDBOX_MCP_HOST_PATH_POLICY | No | Set to 'unrestricted' to allow any host path | allowlist |
| AGENT_SANDBOX_MCP_MAX_OUTPUT_BYTES | No | Default cap for command output, logs, and file reads | 1048576 |
| AGENT_SANDBOX_MCP_DEFAULT_TIMEOUT_MS | No | Default timeout for exec-style operations | 120000 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues