agent-sandbox
by johnnie-code
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token needed only for `sandbox_push` and `sandbox_open_pr`. | |
| SANDBOX_MODE | No | Either `docker` or `local`. Docker mode is the default and runs commands in a container; local mode runs commands on the host. | docker |
| SANDBOX_ROOT | No | Where workspaces live. | /tmp/agent-sandbox/workspaces |
| SANDBOX_IMAGE | No | Image commands run in. | node:22-bookworm |
| SANDBOX_NETWORK | No | Network setting for sandboxed commands. Set to `bridge` only if a build needs the network. | localhost |
| SANDBOX_TIMEOUT_MS | No | Per-command wall-clock timeout in milliseconds. | 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
ActivityMaintained
ResponsivenessNo recent community issues