Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHAT2DSH_ROOTSNoWhitelist of project directories the agent is allowed to work in (used when no --root is given). A cwd outside these roots is rejected.
CHAT2DSH_TOKENNoBearer token required by the HTTP mode; the server refuses to start in HTTP mode without a token unless --no-auth is passed explicitly. Generate with `node -e "console.log(require('crypto').randomBytes(24).toString('hex'))"`.
DEEPSEEK_API_KEYYesDeepSeek API key used by the local DSH agent to execute tasks (obtain from platform.deepseek.com/api_keys). Without it the bridge runs but dsh_run returns MISSING_CREDENTIAL.
CHAT2DSH_MAX_OUTPUTNoMaximum output size before truncation. Defaults to 64 KB.

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