Codex DSH Connect
by lightporta
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| --wsl-cli | No | Windows only: path to this project's bin/codex-dsh-connect.mjs inside the selected WSL2 distribution. | |
| --dsh-root | No | Absolute path to the Harness (@deepseek-ai/dsh) installation directory, if it is not in the default npm location (~/.npm-global/lib/node_modules/@deepseek-ai/dsh). | |
| --wsl-node | No | Windows only: path to the Linux Node executable inside the selected WSL2 distribution, e.g. /usr/bin/node. | |
| --workspace | Yes | Absolute path to an explicitly authorized existing project directory that Harness may read and write. Required; the server refuses delegation until a workspace is configured. | |
| --timeout-ms | No | Per-task timeout in milliseconds (1000–300000). Defaults to 120000 (120 seconds). | |
| --wsl-distro | No | Windows only: name of the explicitly selected WSL2 distribution in which tasks are executed, e.g. Ubuntu-24.04. | |
| --max-requests | No | Maximum number of model generation requests per task (1–16). Defaults to 8. | |
| --credential-file | No | Absolute path to the native Harness credentials file. Defaults to ~/.dsh/.credentials.yaml. The connector never reads or copies its contents. |
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