Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
VIBE_ACP_CWDNoDefault working directory. Defaults to the user home directory.
VIBE_ACP_EXENoACP agent executable, or a command with arguments. Defaults to `vibe-acp` on `PATH`, otherwise the platform install location.vibe-acp
VIBE_ACP_MODENoApproval mode applied when omitted.accept-edits
VIBE_ACP_MODELNoModel applied when a call omits one, using the inference-API id. Unset by default, allowing Vibe to choose its own model.
MISTRAL_API_KEYNoBearer token for the Studio half. Read from this environment variable when set, otherwise from the harness credential store at `$DSH_HOME/.credentials.yaml` or `~/.dsh/.credentials.yaml`.
MISTRAL_MCP_URLNoStudio MCP endpoint.https://api.mistral.ai/mcp
VIBE_ACP_TIMEOUTNoDefault and maximum seconds per prompt.2100000
VIBE_ACP_THINKINGNoThinking level applied when omitted.high
MISTRAL_MCP_TIMEOUTNoStudio request timeout in seconds.90
VIBE_ACP_CANCEL_GRACENoSeconds to wait for a cancel to settle before killing the process.30
VIBE_ACP_IDLE_TIMEOUTNoCancel a prompt that emits no ACP update for this many seconds.1200
VIBE_ACP_TOOL_IDLE_TIMEOUTNoSilence budget in seconds while a tool call is in flight.900
MISTRAL_STUDIO_RETRY_COOLDOWNNoSeconds before a failed Studio connection is retried.60

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