Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEEPSEEK_API_KEYNoYour DeepSeek API key. Recommended to place it in a .env file in the target repository root (not committed), inject it into the environment launching Codex, or configure it later in the Harness page under Settings → Models.
DSH_MCP_DATA_DIRNoPersists each workspace's Harness Web settings and sessions.~/.deep-seek-harness-mcp
DEEPSEEK_BASE_URLNoOptional DeepSeek-compatible API address; defaults to the provider default.
DSH_MCP_NPX_COMMANDNoCustom npx command path.npx
DSH_PERMISSION_MODENoDeepSeek Harness permission mode.workspace-write
DSH_MCP_HARNESS_PACKAGENoExact npm package version used when launching the local Harness process.@deepseek-ai/dsh@0.1.0-rc.6
DSH_MCP_WORKSPACE_ROOTSNoList of absolute root directories that start_run is allowed to use, using the current platform's path separator. Unrestricted by default.

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Maintenance

ActivityMaintained
ResponsivenessNo issues