Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WB_CWDNoDefault working directory used when a call doesn't pass `cwd`.
WB_MODELNoDefault model used when a call doesn't pass `model` (e.g. `hy3`, `deepseek-v4-flash`, `glm-5.3`, `kimi-k3-1`, `auto`).
WB_COMMANDNoThe CLI to drive. If `command not found`, point to the absolute path (e.g. `C:\...\codebuddy.cmd`).codebuddy
WB_TIMEOUTNoDefault per-task timeout in ms (15 min). Tasks exceeding it are killed and partial output is returned. Per call you can pass `timeoutMs` (e.g. `1800000` for long research tasks).900000
WB_FALLBACK_MODELNoModel to auto-switch to when the primary is overloaded/rate-limited (maps to `--fallback-model`, only works with `--print`).
WB_SKIP_PERMISSIONSNo`true` adds `--dangerously-skip-permissions` (needed for scripted file/network tools). Set `false` to keep interactive approval.true

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LinHaiJ/workbuddy-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server