gpt-web-agent
by yyyqt
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| port | No | Port number for the HTTP transport (used when transport is 'http'). | 8788 |
| root | Yes | The workspace root directory. Required to run the server. Example: /tmp/bridge-demo | |
| read-only | No | Set to 'true' to remove write/task-save/shell tools. | false |
| transport | No | Transport type: 'stdio' (default) or 'http'. | stdio |
| allow-codex | No | Set to 'true' to expose the start_codex tool. | false |
| max-seconds | No | Maximum runtime in seconds for shell/Codex jobs. Maximum allowed is 86400. | 600 |
| max-concurrent | No | Maximum number of concurrent jobs. Maximum allowed is 16. | 2 |
| max-file-bytes | No | Maximum bytes for file read/write operations. Maximum allowed is 16777216. | 1048576 |
| allow-host-exec | No | Set to 'true' to enable unsandboxed host shell execution. Off by default. | false |
| max-output-bytes | No | Maximum bytes of command output kept. Maximum allowed is 16777216. | 131072 |
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 issues